Author: Stephane

Datanalysis - Mettons vos données en action Sites > Businesslab > Articles by: Stephane
Clients
20 novembre 20240

IBL testifies: Business Lab Consulting, a key partner for the Wiiv loyalty programme

Training and support
A 360° expertise
Turning Data into action

At Business Lab Consulting, we’re proud to share our customers’ feedback. Today, we’d like to talk to you about IBL and its wiiv loyalty programme, which will be launched in 2019.

The Head of Loyalty, Cécile MASSON HENRY, gives us her impressions of our collaboration.

.

Starting out in a new field

When IBL launched the wiiv programme, the team was ‘new to the field’ and had to ‘wait until we had a minimum amount of data before starting the project’. It was against this backdrop that IBL chose to call on Business Lab Consulting, an agency offering not only skills in data visualisation, but also expertise in loyalty marketing.

The Challenges

IBL faced a number of difficulties during the implementation of the data project for its wiiv loyalty programme:

  • The entire team’s lack of experience and knowledge of the subject; Little feedback on the partners’ real needs in terms of data visualisation, as they themselves had little experience in this area;

 

  • ‘Dashboards poorly adapted to business needs, due to a failure to properly question data and visualisation requirements. The time required for such a project at a time when we were still in the launch phase and undergoing significant growth. We were short of resources and we couldn’t concentrate solely on this project with all its complexities’, explains Cécile M.H, head of the division.

The contribution of Business Lab Consulting

Despite these challenges, the collaboration with Business Lab Consulting has had a significant impact on IBL’s services within this department. The greatest contribution has been in training and support to :

  • Understanding what the data revealed
  • Ask the right questions
  • Learn loyalty programme management concepts
  • Carry out tests
  • Obtain a readable and comprehensible visualisation of the data

ADVANTAGES

During the tender process, Business Lab Consulting stood out as the only agency offering both :

  • Data visualisation and data processing services
  • Expertise in loyalty programmes
  • Customised analysis models
  • Technical and theoretical training

For IBL, this global offer represented real added value and its various advantages made this collaboration possible, says Cécile M.H.

The most appreciated aspects

IBL particularly appreciated the training and support provided by Business Lab Consulting, enabling it to acquire the skills needed to make the most of its data.

Positive developments in monitoring and support

Although there were some initial challenges in terms of monitoring and support due to the dependence on a single consultant, Business Lab Consulting has strengthened its team, enabling it to be more responsive and work more smoothly together.

A global, high-quality service

To sum up, IBL states:

‘With Business Lab Consulting, we had everything under one roof – visualisation expert, loyalty programme expert, data marketing expert and quality training, with the added pleasure of working with people we value and who give a huge amount of themselves to the success of our project.’

A solid recommendation

On a scale of 1 to 10, IBL recommends Business Lab Consulting's services at 8.5/10.

At Business Lab Consulting, we are delighted with the trust placed in us by IBL for its wiiv loyalty programme. We will continue to provide high quality services, taking seriously the areas for improvement that we can always work on, constantly adapting to the evolving needs of our customers in the field of loyalty marketing.

Has this feedback inspired you and echoed certain issues in your company?

Don’t hesitate to contact us, we’ll help you make informed decisions.

I've got a problem, help!
Clients
04 octobre 20240

KDI testifies: Business Lab Consulting, a key data processing partner

Optimized data analysis and visualization
Customized solutions for data processing
Data integration and management

At Business Lab Consulting, we’re proud to share our customers’ feedback. Today, we present a testimonial from KDI, a company that called on our services to optimize its data management and operations. KDI’s Director of Logistics and Procurement gives us his impressions of our collaboration.

Objectives achieved and needs met

“All the major objectives linked to data management and exploitation have been achieved (…)The Business Lab Consulting service has been an invaluable resource for our department, providing invaluable assistance in decision-making”, emphasizes our customer.

The applications we have developed meet all KDI’s initial needs, whether in terms of data analysis, visualization or integration.

Our collaboration has enabled KDI to better understand and analyze their business, by providing clear tools and solutions to effectively exploit their data and improve their overall performance.

Why did KDI turn to BLC?

KDI’s decision to call on our services was based on two key factors:

  1. The continuity of a successful past collaboration
  2. Positive feedback on our expertise

Two aspects of our service were particularly appreciated:

  1. Our constant availability
  2. Efficient collaboration between the various parties involved

ADVANTAGES

KDI highlights two major advantages of Business Lab Consulting:

  1. Our expertise
  2. Our ability to propose different approaches to best meet their expectations
  3. Quality follow-up and support

These strengths have enabled KDI to obtain tailor-made solutions, perfectly adapted to their needs.

“Nothing to complain about, the follow-up and support have been very good. The team is responsive on the whole”, says our customer.

A complete and rewarding service

KDI rates his satisfaction at 9/10, a score that reflects the high quality of our services. The Logistics and Procurement Manager says he would recommend Business Lab Consulting without hesitation.

In conclusion, KDI sums up our service in the following terms:

 

“Your service combines efficiency, expertise, data control and provides real added value.”

 

At Business Lab Consulting, we are delighted with the trust placed in us by KDI, and will continue to provide services of the highest quality to meet our customers’ data management and exploitation needs.

Has this feedback inspired you, and echoed some of the issues present in your company?

Don’t hesitate to contact us, we’ll help you make informed decisions.

I have a problem, help!
Artificial Intelligence, Data Governance, Data Marketing, Data Mining and Data Integration, Data visualisation
11 septembre 20240

DATA: 7 Pitfalls to Avoid, Ep 7/7 – Design dangers

The Critical Role of Design in Data Presentation

As Steve Jobs once said, « Design is not just what it looks like and feels like. Design is how it works. » This principle applies perfectly to data visualization. In this final episode of our series, we’ll explore the often-overlooked dangers related to design in data presentation.

Pitfall 7A: Confusing colors

Color choice is a crucial aspect of data visualization design, yet it’s often mishandled. Poorly chosen colors can make visualizations difficult to read or even misleading. Here are some common color-related pitfalls:

  1. Using too many colors: This can visually overwhelm and make understanding difficult.
  2. Choosing colors that don’t contrast well: This can make it challenging to differentiate between categories.
  3. Ignoring color blindness: Some color combinations can be indistinguishable for color-blind individuals.
  4. Using the same color for different variables: This can lead to confusion and misinterpretation.

Consider this example of a poorly designed dashboard:

In this dashboard, the use of similar colors for different categories makes it difficult to distinguish between crime types. A better approach would be to use a clear, distinct color palette with high contrast between categories.

Pitfall 7B: Missed opportunities

Sometimes, in our quest for simplicity, we miss opportunities to enhance understanding through design. Thoughtful addition of visual elements can greatly improve engagement and memorability.

For example, consider this improved visualization of Edgar Allan Poe’s works:

This visualization uses design elements to evoke the dark ambiance of Poe’s works, making the visualization more memorable and engaging. The inverted y-axis and blood-red color scheme add to the ominous feel, while the portrait and signature provide context and personality.

Pitfall 7C: Usability Uh-Ohs

Good design isn’t just about visual appeal; it must also consider usability. Visualizations that are difficult to manipulate or understand can frustrate users and limit the effectiveness of data communication.

Key usability considerations include:

  • Intuitive navigation: Users should easily understand how to interact with the visualization.
  • Clear labeling: All elements should be clearly labeled to avoid confusion.
  • Responsive design: Visualizations should work well on various devices and screen sizes.
  • Accessibility: Design should accommodate users with different abilities.

Here’s an example of a dashboard with potential usability issues:

While this dashboard offers numerous interaction options, without careful user interface design, it can become overwhelming and difficult to use effectively. A better approach would be to simplify the interface, prioritize key information, and provide clear guidance on how to interact with the visualization.

CONCLUSION

In this final article of our series, we’ve explored the seventh type of error we can encounter when working with data: design dangers. We’ve seen how color choices, missed opportunities, and usability issues can affect the effectiveness of our data visualizations.

Throughout this seven-part series, we’ve covered a wide range of common pitfalls in working with data, from how we think about data to how we present it. By being aware of these pitfalls and learning how to avoid them, we can significantly improve our ability to work effectively with data and communicate valuable insights.

Remember, good design in data visualization is not just about making things look pretty. It’s about enhancing understanding, facilitating insights, and enabling better decision-making. As you continue your data journey, keep these principles in mind to create visualizations that are not only visually appealing but also clear, informative, and user-friendly.

This series of articles is strongly inspired by the book « Avoiding Data Pitfalls – How to Steer Clear of Common Blunders When Working with Data and Presenting Analysis and Visualizations » written by Ben Jones, Founder and CEO of Data Literacy, WILEY edition. We highly recommend this excellent read to deepen your understanding of data-related pitfalls and how to avoid them!

You can find all the topics covered in this series here: https://www.businesslab.mu/blog/artificial-intelligence/data-7-pitfalls-to-avoid-the-introduction/

Artificial Intelligence, Business Intelligence, Company, Data Governance, Data Marketing, Data Mining and Data Integration, Machine Learning, Self-service Analytics
11 septembre 20240

Lean UX Design: the key to revolutionizing your BI development

What is Lean UX Design and why is it crucial to your BI?

In the dynamic world of Business Intelligence (BI), where the complexity of data meets the evolving needs of users, Lean UX Design is emerging as a revolutionary approach. This user-centered methodology promises to radically transform the way we design and develop BI solutions.

Lean UX design in brief

  • User-centered approach
  • Rapid iterations and continuous feedback
  • Cross-functional collaboration
  • Waste reduction and resource optimization
  • Agile adaptation to change
But how can Lean UX concretely improve your BI projects? Let’s delve into the details.

The 5 key steps of the Lean UX process in BI

  1. Problem and user definition: gain an in-depth understanding of your BI users’ specific challenges.
  2. Ideation and hypotheses: formulate hypotheses about potential solutions.
  3. Rapid prototyping: create low-fidelity prototypes to test your ideas.
  4. User testing: get rapid feedback to validate or invalidate your hypotheses.

The tangible benefits of Lean UX in BI development

1. Significant reduction in development time and costs

By quickly identifying what works and what doesn’t, Lean UX saves precious resources.

“Thanks to DATANALYSIS’ Lean UX approach, we reduced our BI development costs by 30% while increasing user satisfaction by 50%.”

– Marie Dupont, CIO, TechInnovate SA

2. Improved user experience and adoption of BI tools

BI solutions designed with users, for users, guarantee better adoption and use.

3. Greater agility and adaptability to market changes

In an ever-changing BI environment, Lean UX enables you to pivot quickly and efficiently.

Here are the 5 steps to implementing Lean UX in your BI projects :

Download our free guide

Integrating Lean UX into your BI strategy: where to start?

Adopting Lean UX in your BI development can seem daunting.

Here are some steps to get you started:

  1. Assess your current UX maturity
  2. Train your teams in Lean UX principles
  3. Start with a pilot project
  4. Measure and communicate results
  5. Gradually extend the approach to other projects

CONCLUSION

In a world where data is king, Lean UX offers a way to turn that data into actionable insights faster and more accurately than ever before. For companies looking to make the most of their BI investments, Lean UX isn’t just an option, it’s a competitive necessity.

At BUSINESS LAB CONSULTING, we’re passionate about applying Lean UX to BI development. Our team of experts is ready to guide you through this transformation to optimize your processes, reduce your costs and significantly improve the user experience of your BI solutions.

Want to learn more ?
Schedule a free consultation with our Lean UX experts
Let's talk !
Data Governance, Data Marketing, Data Mining and Data Integration, Data visualisation, Machine Learning, Self-service Analytics
05 septembre 20240

DATA: 7 Pitfalls to Avoid, Ep 6/7 – Graphical blunders

How to Avoid Common Errors in Data Visualization

Data visualization is a powerful tool for communicating complex information clearly and concisely. However, it can also be a source of numerous errors that can lead to misinterpretations. In this episode, we’ll explore the most common graphical gaffes and how to avoid them.

Pitfall 6A: Misleading Graphs

One of the most common pitfalls in data visualization is creating graphs that mislead, often unintentionally. This can happen in several ways:

  1. Truncating the Y-axis: By not starting the Y-axis at zero, visual differences between values can be exaggerated.
  2. Choosing an inappropriate scale: A poorly chosen scale can hide or exaggerate important trends.
  3. Using 3D graphs: 3D graphs can distort the perception of proportions.

For example, consider this graph showing drug-related crime cases in Orlando:

This graph seems to show an alarming increase in drug-related crimes. However, upon closer examination, we see that the Y-axis doesn’t start at zero, visually exaggerating the increase.

Pitfall 6B: Data Dogmatism

It’s easy to fall into the trap of data dogmatism, thinking there’s only one « right » way to visualize data. In reality, the choice of graph type depends on the context, audience, and message you want to convey.

For example, although pie charts are often criticized, they can be effective for showing parts of a whole, especially when there are few categories:

This pie chart clearly shows that theft accounts for nearly half of all reported crimes in Orlando.

Pitfall 6C: The false optimization/satisfaction dichotomy

In data visualization, one can fall into the trap of thinking that we must always seek the « optimal » visualization at the expense of « satisfactory » solutions. In reality, it’s often more practical and effective to find a visualization that meets the needs sufficiently well, rather than spending excessive time seeking perfection.

For example, this horizontal bar chart can be « satisfactory » for showing the most common types of crimes, even if it’s not necessarily « optimal »:

This graph is easy to understand and quickly provides essential information, even if it could potentially be optimized further.

CONCLUSION

In this article, we explored the sixth type of error we can encounter when working with data: graphical gaffes. We’ve seen how to avoid misleading graphs, data dogmatism, and the false dichotomy between optimization and satisfaction.

In the next and final article in our series, we’ll explore the 7th type of error: design dangers. We’ll see how design choices can affect the perception and interpretation of visualized data.

This series of articles is strongly inspired by the book « Avoiding Data Pitfalls – How to Steer Clear of Common Blunders When Working with Data and Presenting Analysis and Visualizations » written by Ben Jones, Founder and CEO of Data Literacy, WILEY edition. We highly recommend this excellent read to deepen your understanding of data-related pitfalls and how to avoid them!

You can find all the topics covered in this series here: https://www.businesslab.mu/blog/artificial-intelligence/data-7-pitfalls-to-avoid-the-introduction/

Business Intelligence, Data Governance, Data Marketing, Data Mining and Data Integration, Data Quality Management, Data Regulations, Data visualisation, Machine Learning, Self-service Analytics
05 septembre 20240

DATA: 7 Pitfalls to Avoid, Ep 5/7 – Analytical aberrations

Intuition and Analysis are Not Mutually Exclusive

In our quest to make the most of data, we often fall into the trap of considering intuition and analysis as mutually exclusive approaches. However, as we’ll see in this episode on analytical aberrations, intuition plays a crucial role in the data analysis process.

Pitfall 5A: the False Intuition/Analysis Dichotomy

There was a time when advertisements boasted about moving from intuition to analysis in decision-making. This view is mistaken. Intuition isn’t obsolete in the data age – it’s actually more valuable than ever.

Intuition is the spark that powers the engine of analysis. It helps us:

  1. Know WHY the data is important
  2. Understand WHAT the data is telling us (and isn’t telling us)
  3. Know WHERE to look next
  4. Know WHEN to stop analyzing and take action
  5. Know WHO needs to hear the results and HOW to communicate them

Pitfall 5B: Exuberant Extrapolations

Predicting the future from data can be risky. Extrapolating current trends can lead to significant errors if we don’t account for natural limits or potential changes.

For example, if we look at life expectancy in North and South Korea from 1960 to 1980, we might be tempted to predict a continuous, linear increase. However, reality turned out quite differently, especially for North Korea, which experienced a significant decline in the 1990s.

Pitfall 5C: Ill-Advised Interpolations

When working with time-series data, we must be careful in our interpretations between data points. A simple slope graph connecting two points in time can mask significant fluctuations between these points.

For example, consider life expectancy in certain countries between 1960 and 2015. A simple slope graph showing the change between these two years could give the impression of a steady and constant increase. However, this simplified representation would mask periods of conflict, economic hardship, or rapid progress in public health that significantly impacted life expectancy over the years.

Take the case of Cambodia, Timor-Leste, Sierra Leone, and Rwanda. A simple slope graph would show an increase in life expectancy between 1960 and 2015, but would completely obscure the tragic periods of war and genocide these countries experienced. For instance, life expectancy in Cambodia fell to less than 20 years in 1977 and 1978, a crucial fact that would be completely ignored in a simple interpolation between 1960 and 2015.

This graph shows the actual evolution of life expectancy in these countries, revealing the dramatic fluctuations masked by a simple linear interpolation.

Pitfall 5D: Funky Forecasts

Forecasts, especially long-term ones, can be particularly prone to errors. A striking example is the unemployment forecasts made by different U.S. presidential administrations. These forecasts tend to show a rapid return to a « normal » rate of 4-6%, regardless of the actual economic situation.

This phenomenon can be explained by several factors. First, there’s political pressure to present optimistic outlooks. Second, there’s a natural tendency to assume that extreme or unusual situations will correct themselves quickly. Finally, forecasting models are often based on historical data and may not adequately account for structural changes in the economy.

For example, during the 2008 financial crisis, unemployment forecasts made just before or at the beginning of the crisis failed to anticipate the magnitude and duration of the increase in unemployment. Similarly, forecasts made at the height of the crisis often underestimated the time it would take for the unemployment rate to return to pre-crisis levels.

This graph shows how different presidential administrations have consistently predicted a rapid return to a « normal » unemployment rate, even in the face of very different economic realities.

Pitfall 5E: Moronic Measures

It’s crucial to ensure that the measures we use are relevant and meaningful. Too often, we focus on measures that are easy to obtain rather than those that are truly important for understanding a phenomenon or making decisions.

In sports, for example, many traditional measures can be misleading. Take the case of professional basketball: a player’s average speed on the court might seem like an interesting measure, but it doesn’t necessarily reflect the player’s real impact on the game.

LeBron James, one of the best players of all time, was criticized during the 2018 playoffs for having the lowest average speed on the court. However, this measure didn’t account for his real impact on the game, measured by more relevant statistics like the Player Impact Estimate (PIE).

This graph shows the relationship between average speed and PIE for NBA players. We can see that LeBron James (point in the top left) has a very high PIE despite a relatively low average speed, illustrating why average speed alone is an inadequate measure of a player’s performance.

This case illustrates the importance of choosing measures that truly reflect what we’re trying to evaluate, rather than settling for measures that are easy to obtain but potentially misleading.

In this article, we explored the fifth type of error we can encounter when using data to illuminate the world around us: analytical aberrations. We’ve seen how intuition and analysis can work together, and how to avoid the pitfalls of exuberant extrapolations, ill-advised interpolations, funky forecasts, and moronic measures.

In the next article, we’ll explore the 6th type of error in our series: graphical gaffes. We’ll see how errors in data visualization can lead to misinterpretations and poorly informed decisions.

This series of articles is strongly inspired by the book « Avoiding Data Pitfalls – How to Steer Clear of Common Blunders When Working with Data and Presenting Analysis and Visualizations » written by Ben Jones, Founder and CEO of Data Literacy, WILEY edition. We highly recommend this excellent read to deepen your understanding of data-related pitfalls and how to avoid them!

You can find all the topics covered in this series here: https://www.businesslab.mu/blog/artificial-intelligence/data-7-pitfalls-to-avoid-the-introduction/

Artificial Intelligence, Business Intelligence, Data Governance, Data Marketing, Data Mining and Data Integration, Data Quality Management, Data Regulations, Data visualisation, Machine Learning, Self-service Analytics
05 septembre 20240

DATA: 7 pitfalls to avoid, Ep 4/7 – Statistical errors – Facts are stubborn things, but statistics are malleable

“There are lies, damned lies and statistics” B.Disraeli

 

Why such distaste for a field that, according to Webster’s Merriam-dictionary, is simply “a branch of mathematics dealing with the collection, analysis, interpretation and presentation of masses of numerical data. ”1 Why is the field of statistics in such a negative light by so many people?

There are four main reasons

  • It’s a complex field. Even the basic concepts are not easily accessible and are very difficult to explain.
  • Even the best-intentioned experts can misapply the tools at their disposal.
  • The third reason behind all this hatred is that those with an agenda can easily create statistics to lie about when communicating with us.
  • The final reason is that statistics can often seem cold and distant, making them very difficult for the public to grasp.

Descriptive setbacks

Descriptive statistics are intended to summarize the main characteristics of a data set. However, incorrect or inappropriate use can lead to misleading conclusions. A typical example is the use of the mean to summarize a distribution, without taking into account variability or skewness. Another common error is to present percentages without explaining the total number of people, which can be misleading as to the true extent of a phenomenon. It is therefore crucial to understand the assumptions and limitations of each descriptive measure in order to use it correctly.

Let’s take the example of analyzing salaries within a company. If we simply look at average salaries, we might conclude that the company is paying its employees well. However, if management salaries are very high compared to the rest of the employees, the average would be biased upwards. It would be more relevant to use the median, which gives the salary in the middle, or to look at the complete salary distribution for a more accurate view.

This error is very well described here with cats:

Inferential fires

Always a feline explanation:

Statistical inference aims to draw conclusions about a population from a sample of that population. However, this process is subject to error. Sampling errors and Type I and II errors are common. In addition, errors can be exacerbated by confusion between correlation and causation. A solid understanding of the principles of statistical inference is essential to avoid these pitfalls.

Let’s imagine a public health study seeking to establish a link between a particular dietary habit (such as eating organic) and better overall health. If the study finds a positive correlation, it doesn’t necessarily mean that eating organic causes better health. There could be confounding factors, such as income level or lifestyle, that influence both eating habits and health status. Here, we can fall into the trap of confusing correlation with causation.

Sliding sampling

Sampling is a crucial stage in any data collection process. Yet many errors can occur at this stage. The sample may not be representative of the target population, due to selection bias or non-response. What’s more, the sample size may be insufficient to detect an effect. Careful sample planning is therefore essential to obtain reliable results.

Consider a customer satisfaction survey conducted by an e-commerce company. If the company only solicits opinions from customers who have made a recent purchase, it runs the risk of obtaining a distorted picture of overall customer satisfaction. Indeed, dissatisfied customers may have stopped making purchases and therefore not be included in the sample. This is an example of selection bias.

Insensitivity to sample size

A common mistake in data analysis is to ignore the impact of sample size on results. A large sample size can make a very small effect significant, while too small a sample size may not have sufficient power to detect an existing effect. Furthermore, statistical significance does not necessarily mean practical significance. So it’s important to consider sample size when interpreting results.

Suppose you’re conducting a study to assess the effect of a drug on lowering blood pressure. If you have a very large sample of patients, you may see a statistically significant drop in blood pressure. However, this drop may be very small, say 0.1 mm Hg, a clinically insignificant value despite its statistical significance. This is an example where sample size can make a small effect significant. On the other hand, if the sample is too small, a real effect may be missed. It is therefore important to consider clinical or practical significance in addition to statistical significance.

Digging deeper into this issue, Ben Jones (see author who inspired this article) managed to find figures on kidney cancer rates as well as demographics for every US county, and he created an interactive dashboard (figure below) to visually illustrate the fact that Kahneman, Wainer and Zwerlink are doing quite clearly in words.

Notice a few elements in the dashboard. On the choropleth map (filled in), the darkest orange counties (high rates relative to the overall U.S. rate) and the darkest blue counties (low rates relative to the overall U.S. rate) are often side by side.

Also, note how in the scatterplot below the map, the marks form a funnel shape, with less populated counties (on the left) more likely to deviate from the reference line (the overall U.S. rate), and more populated counties like Chicago, L.A. and New York are more likely to be close to the overall reference line.

 

One final observation: if you hover over a county with a small population in the interactive online version, you’ll notice that the average number of cases per year is extremely low, sometimes 4 cases or less. A small deviation – even just 1 or 2 cases – in a subsequent year will pull a county from the bottom of the list to the top, or vice versa.

 

In the next article, we’ll explore the 5th type of error we may encounter when using data to illuminate the world around us: Analytical aberrations.

This article is heavily inspired by the book “Avoiding Data pitfalls – How to steer clear of common blunders when working with Data and presenting Analysis and visualization” written by Ben Jones, Founder and CEO of Data Litercy, WILEY edition. We recommend this excellent read!

You can find all the topics covered in this series here: https://www.businesslab.mu/blog/artificial-intelligence/data-7-pitfalls-to-avoid-the-introduction/

Business Intelligence, Data Governance, Data Marketing, Data Mining and Data Integration, Data Regulations, Machine Learning, Self-service Analytics, Technology
05 septembre 20240

DATA: 7 pitfalls to avoid. Ep 3/7 – Mathematical errors: how are data calculated?

We’ve all expressed disbelief at the relevance of mathematics to our daily lives. What purpose could this dense, complex subject possibly serve? Well, in a world where data is everywhere and infuses every strategic decision made by organizations, mathematics is vitally important (editor’s note: it always has been!).

In our data analysis projects, mathematical errors can occur as soon as a calculated field is created to generate additional information from our initial dataset. This type of error can be found, for example, when :

  • We perform aggregations (sum, mean, median, minimum, maximum, count, separate count etc.) at different levels of detail
  • We make divisions to produce ratios or percentages
  • We work with different units

These are obviously just a few of the types of operation where errors can occur. But in our experience, these are the main causes of the problems we encounter.

And, in each of these cases, it doesn’t take a genius engineer or scientist to correct them. It just takes a little care and a lot of rigor!

1. Unit processing errors

In this article, we won’t dwell too much on this common mistake. In fact, there are a large number of articles and anecdotes which illustrate this type of problem perfectly and in detail (which we also discussed in the previous article).

The most famous and costly example is the crash of the Mars Orbiter probe. If you’d like to find out more, please click here: Mars Climate Orbiter – Wikipedia

You may argue that none of us is part of NASA and has to land a probe on a distant planet, so we’re not concerned. Well, you may well come across this type of error when handling time data (hours, days, seconds, minutes, years), financial data (different currencies), or managing stocks (units, kilos, pallets, bars etc.).

2. Aggravation of aggregations

We aggregate data when we group records that have an attribute in common. There are all sorts of such groupings that we deal with in our world as soon as we can establish hierarchical links; time (day, week, month, year), geography (cities, region, country), organizations (employees, teams, companies) and so on.

Aggregations are a powerful tool for apprehending the world, but beware, they involve several risk factors:

  • Aggregations summarize a situation and do not present detailed information. Anyone who has taken part in a datavisualization training course with our teams is familiar with Anscombe’s quarter:

The statistical summary is a typical example of what aggregates can hide. In this example, the four data sets have exactly the same sums, means and standard deviations on both coordinates (X,Y). When we plot each of the points on curves, it’s easy to see that the 4 stories are significantly different.

As soon as data is aggregated, we try to summarize a situation. We must always remember that this summary masks the details and context that explain it. So be careful when, in a discussion, your interlocutors only talk about average values, sums or medians, without going into the details of what may have led to that particular scenario.

  • Aggregations can also mask missing values and be misleading. Indeed, depending on the way we represent information, the fact that data is missing may not be clearly visible at first glance.

Take, for example, a dataset in which we observe the number of bird strikes on aircraft for an airline.

Our objective is to determine the month(s) of the year with the most incidents. This gives :

July appears to be the month with the highest number of impacts counted. However, if we look at the details by year, we realize that the aggregation chosen to answer our question did not allow us to determine that the seizures for the year 2017 stopped during this famous month of July:

The answer to our question was therefore August, if we exclude the data for the year for which we didn’t have all the records.

  • Totals and aggregations :

This is the last example of the problems linked to aggregations that we’re going to discover in this article. This is one of the author’s “favorite” mistakes. Some might even call it a specialty!

It comes into play when it’s necessary to count the distinct individuals in a given population. Let’s say we’re looking at our customer base and want to know how many unique individuals are in it.

Counting the distinct ids for the whole company gives us a count of our unique customers:

But if we look at each product line and display a sum without paying attention :

We found 7 more customers!

This happens simply because there are customers in the customer base of the company studied who take both services AND licenses, and who end up being counted twice in the total!

This is a problem with simple solutions in all modern datavisualization and BI software, but it tends to hide itself in a series of calculations and aggregations, causing sometimes surprising discrepancies at the end of the chain.

3. Panic on board, a ratio!

We’ll illustrate this point with an example taken from one of the dashboards we made for one of our customers. With all our expertise, we also sometimes jump headlong into this type of error:

And yes, we’re talking about an occupancy rate that’s “slightly” over 100%!

How is this possible? A simple oversight!

The sum of the divisions is not equal to the division of the sums…

In this case, we had a data set similar to the one below:

Is the occupancy rate equal to :

The sum of the individual occupancy rates? FALSE!

This gives us a total of 30% + 71% + 100% + 50% + 92% + 70%, i.e. 414%.

And that’s exactly the error we made on an even larger data set…

Or the ratio of total passengers to total available capacity? 125/146 = 86%. That’s more accurate!

Note: the average of individual occupancy rates would also be wrong.

In short, whenever a ratio is manipulated, it’s a question of dividing the total of the numerator and denominator values to avoid this type of problem.

This is just one example of a ratio error. Honorable mentions can be given to the treatment of NULL values in a calculation, or to the comparison of ratios that are not calculated with the same denominators.

In the next article, we’ll explore the 4th type of obstacle we may encounter when using data to shed light on the world around us:

Statistical slippage. (Spoilers: “There are lies, damned lies and statistics” B.Disraeli)

This article was strongly inspired by the book “Avoiding Data pitfalls – How to steer clear of common blunders when working with Data and presenting Analysis and visualization” written by Ben Jones, Founder and CEO of Data Litercy, WILEY edition. We recommend this excellent read!

You can find all the topics covered in this series here: https://www.businesslab.mu/blog/artificial-intelligence/data-7-pitfalls-to-avoid-ep-2-7-technical-errors-how-is-data-created/

Business Intelligence, Company, CRM, Data Governance, Data Marketing, Data Mining and Data Integration, Data Quality Management, Data Regulations, Machine Learning, Self-service Analytics
04 septembre 20240

DATA: 7 pitfalls to avoid. Ep 2/7 – Technical errors: how is data created?

Having defined a few key data-related concepts, we can now delve into the technical issues that can lead to errors. This article deals with the problems associated with the process of obtaining the data that will subsequently be used. It’s about building the foundations of our analyses.

And it goes without saying that we don’t want to build a house of cards on sand!

To stay with the construction metaphor, if problems of this nature exist, they will be hidden and barely visible in the final building. Particular care must therefore be taken during the data collection, processing and cleaning stages. It’s not for nothing that it’s estimated that 80% of the time spent on a data science project is spent on this type of task.

To avoid falling into this trap, and to limit the load required to carry out these potentially tedious operations, we need to accept three fundamental principles:

  • Virtually all datasets are not clean and need to be cleaned and formatted.
  • Each transition (formatting, join, link, etc.) during the preparation stages is a potential source of new error
  • It is possible to learn techniques to avoid the creation of errors arising from the first two principles.

Accepting these principles does not remove the obligation to go through this preliminary work before any analysis, but the good news is that knowing how to identify these risks, and learning as we go along, helps to limit the scope of this second obstacle.

1. The trap of dirty data.

Data is dirty. I’d even go so far as to say that all data is dirty (see first principle above), with problems of formatting, data entry, inconsistent units, NULL values and so on.

Some well-known examples of this trap

Take the crash of NASA’s Mars Climate Orbiter in 1999, for example. A $125 million error caused by a dual unit system: imperial and metric units. This led to an erroneous calculation that affected the power sent to the probe’s thrusters and its destruction.

Fortunately, not all errors of this nature will cost us so much money! But they do have a significant impact on the results and ROI of the analyses we carry out.

So, at DATANALYSIS, we’re currently running several projects specifically on data quality in the context of DATA Marketing, and we’re dealing with two types of subject:

  • Data validation, which aims to improve data quality through data processing, by :

-Standardizing fields (phone number, email, etc.): +262 692 00 11 22 / 00262692001122 / 06-92-00-11-22 correspond to the same line, and we can automate much of this work thanks to appropriate processing;

– Filling in empty fields using other data in the table. For example, we can deduce the country of residence from telephone numbers, zip codes, cities, etc.

 

  • Deduplication, by :

-Using adapted rules to identify potentially identical lines. Two records with the same e-mail address, telephone number or company ID;

-Using distance calculation algorithms to define similar values in terms of spelling, pronunciation, common characters, etc.

From these examples and our own experience, we can see that this type of error mainly stems from data entry, collection or “scrapping” processes, whether implemented automatically or by humans. So, in addition to the solutions that can be implemented in data preparation processes, improving these preliminary steps will also greatly improve the quality of the data to be processed, and this requires education, training and the definition of rules and standards that are clearly known and shared (data governance is never far away).

Finally, we should also ask ourselves when we can consider this stage to be sufficiently clean. After all, we can always do more and better, but the costs involved can often outweigh the expected returns.

2. The data transformation trap

In the IT world, there’s an image that sums up this type of problem:

Often, the mistake lies between the screen and the seat!

And yes, even the best data scientists, data analysts or data engineers can make mistakes in the data cleansing, transformation and preparation stages.

Frequently, we manipulate several files from different sources and different applications, which multiplies the risks associated with dirty data issues and the risks when manipulating the files themselves:

  • Different levels of granularity
  • Joins on fields whose values are not exactly identical (e.g. ST-DENIS vs SAINT DENIS).
  • Different file perimeters

And this problem can also be made more complex depending on the tools used in our analyses:

  • In Tableau, for example, we can perform data joins, relations or links to link several datasets together. Each type of operation has its own rules and constraints.
  • In Qlik, you need to understand how the associative engine works and the associated modeling rules, which differ from those of a traditional BI model.

In this case, it’s often a question of technical constraints linked to the very business of data preparation, and taking the time to understand the risks and processes in place will save a great deal of time in delivering reliable, high-performance data analysis.

In the next article, we’ll explore the 3rd type of obstacle we may encounter when using data to shed light on the world around us: Mathematical errors.

This article was strongly inspired by the book “Avoiding Data pitfalls – How to steer clear of common blunders when working with Data and presenting Analysis and visualization” written by Ben Jones, Founder and CEO of Data Litercy, WILEY edition. We recommend this excellent read!

You can find all the topics covered in this series here : https://www.businesslab.mu/blog/artificial-intelligence/data-7-pitfalls-to-avoid-ep-1-7-epistemological-errors-how-do-we-think-about-data/

Artificial Intelligence, Business Intelligence, Company, Data Governance, Data Marketing, Data Mining and Data Integration, Data Quality Management, Data Regulations, Machine Learning
04 septembre 20240

DATA: 7 pitfalls to avoid. Ep 1/7 – Epistemological errors: how do we think about data?

Let’s start by defining what epistemology is.

Epistemology (from the ancient Greek ἐπιστήμη / epistémê “true knowledge, science” and λόγος / lógos “discourse”) is a field of philosophy that can refer to two fields of study: the critical study of science and of scientific knowledge (or scientific work).
In other words, it’s about how we construct our knowledge.

In the world of data, this is a central and critical topic. We are familiar with the process of transforming data into information, knowledge and wisdom:

Here, the problem lies in the way we consider our starting point: data! Indeed, the use of data and its transformation in the following stages are the result of conscious and controlled processes and procedures:

==>I clean up my data, process it in an ETL / ELT, store it, visualize it, communicate my results and share them, and so on. This mastery gives us control over the quality of each step. However, we tend to embark on this work of transforming our primary resource while overlooking a crucial point, the source of our first obstacle:

DATA IS NOT AN EXACT REPRESENTATION OF THE REAL WORLD!

Indeed, it’s all too easy to work with data by thinking of data as reality itself, and not as data collected about reality. This nuance is essential:

It’s not crime, but reported crime
It’s not the diameter of a mechanical part, but the measured diameter of that part.
It’s not public sentiment on a subject, but the declared feeling of those who responded to a survey.

Let’s go into the details of this obstacle with a few examples:

1. What we don't measure (or didn't measure)

Let’s take a look at this dashboard showing all the meteorite impacts on Earth between -2500 and 2012. Can you identify what’s strange here?

Source: Meteorite fall on Earth visualized | Tableau Public

Meteorites seem to have carefully avoided certain parts of the planet – a large part of South America, Africa, Russia, Greenland, etc. And if we focus on the graph showing the number of meteorites per year, these have tended to fall more in the last 50 years (and almost not over the whole period covering -2055 to 1975).

Is this really the case? Or rather flaws in the way the data was collected?

  • We have recently begun to systematically collect this information and rely on archaeology to try and determine the impacts of the past. As erosion and time have taken their toll, the traces of the vast majority of impacts have disappeared and can no longer be counted (and no, meteorites didn’t start raining in 1975).
  • For a meteorite impact to be included in a database, it has to be recorded. And to do that, you need an observation, and therefore an observer, who knows who to report it to. These two biases have a major impact on data collection, and help to explain the large areas of the Earth that seem to have been spared by the meteorite fall.

2. Measurement system not working

Sometimes, the cause of this discrepancy between data and reality can be explained by a defect in the collection equipment. Unfortunately, anything manufactured by a human being in this world is liable to fail. This applies to sensors and measuring instruments, of course.

What happened on April 28 and 29, 2014 on this bridge? There seems to have been a huge spike in bicycle traffic across the Fremont Bridge, but only in one direction (blue curve).

Source : 7 datapitfalls – Ben Jones

Time series of the number of bicycles crossing the Fremont Bridge

You’d think it was a beautiful summer’s day and everyone was on the bridge at the same time? That it was a one-way bike race? That everyone who crossed the bridge on the outward journey had a flat tire on the return journey?

More prosaically, it turns out that the blue counter had a fault on those particular days and was no longer counting bridge crossings correctly. A simple change of battery and sensor solved the problem.

Now, ask yourself how many times you’ve been misled by data from a faulty sensor or measurement without being aware of it?

3. Data is too human

And yes, our own human biases have a major effect on the values we record when gathering information. We tend, for example, to round off measurement results:

Source : 7 datapitfalls – Ben Jones

If we go by his data, diaper changes take place more regularly every 10 minutes (0, 10, 20, 30, 40, 50) and sometimes over certain quarters of an hour (15, 45). Wouldn’t that be incredible?

It is an incredible story. In fact, we need to look at how the data was collected. As human beings, we have this tendency to round up information when we record it, especially when we look at a watch or clock: why not indicate 1:05 when it’s 1:04? Or even simpler, 1:00, because it’s even simpler?

4. The Black Swan!

The final example we’d like to highlight here is the so-called “Black Swan” effect. If we think that the data we have at our disposal is an accurate representation of the world around us, and that we can extract from it assertions to be set in stone; then we are fundamentally mistaken about what data is (see above).

The best use of data is to learn what isn’t true from a preconceived idea, and to guide us in the questions we need to ask ourselves to learn more?

But back to our black swan:

Before the discovery of Australia, every swan sighting ever made could confirm to Europeans that all swans were white – wrong! In 1697, the sighting of a black swan completely challenged this common preconception.

And the link with the data? In the same way that we tend to believe that a repeated observation is a general truth – wrongly so – we can be led to infer that what we see in the data we manipulate can be applied generally to the world around us and to any era. This is a fundamental error in the appreciation of data.

5. How to avoid epistemological error?

All it takes is a little mental gymnastics and a little curiosity:

  • Clearly understand how measurements are defined
  • Understand and represent the data collection process
  • Identify possible limitations and measurement errors in the data used
  • Identify changes in measurement methods and tools over time
  • Understand the motivations of data collectors

In the next article, we’ll explore the 2nd type of obstacle we may encounter when using data to illuminate the world around us: Technical Mistakes.

This article is heavily inspired by the book “Avoiding Data pitfalls – How to steer clear of common blunders when working with Data and presenting Analysis and visualization” written by Ben Jones, Founder and CEO of Data Litercy, WILEY edition. We recommend this excellent read!

You can find all the topics covered in this series here : https://www.businesslab.mu/blog/artificial-intelligence/data-7-pitfalls-to-avoid-the-introduction/