Lekiro - Blog #Analytics

Analytics on a budget

Fri, 15 Jul 2022 16:03:08 +0200

Small budgets in young businesses are frustrating. They prevent to address all seemingly urgent questions about R&D and business strategies with analytics. How to handle this?

You need to prioritize these questions and work with analysts with strong listening capacities to understand your field, your needs, and your resources.They should also be in the habitof working with different methods and dataset sizes to be able to adapt to the context of your business.

To prioritize your questions, the first step consists in establishing a list of all the needs of your teams. The perspectives of all those individuals might differ, and it can be enlightening to hear their views to take proper decisions. Their expertise will also be important for the following steps.

Afterward, you can organize meetings between employees and analysts to rank the needs according to their expected benefits and feasibility. Here are some of the points to discuss during these meetings:

Translate needs into questions and hypotheses (e.g., Need = finding new procedures to increase customer retention / Question = which procedures X, Y, or Z improve the most customer retention? / One of the hypotheses = X benefits more the customer retention than Y)? The analysts will help with the formulation of the questions and hypotheses.
Exclude needs which cannot be translated into questions addressable with analytics.
Estimate the gain and loss of conducting or not an analysis to address each need. If you have a new procedure in mind, how much do you expect to lose if you apply this procedure when it does not provide any improvements. Same question if you do not apply it when it does provide some significant improvements? Here answering these questions strongly depends on the expertise of your non-analyst teams, but analysts can help with estimations. This step will help to estimate the expected benefits of conducting each analysis.

Communicate to the analysts the size effects which will make a difference to the business performances. Do you need at least 10% increases in customer retention to make a real difference? This information will condition the size of data sets needed (see below).
Share with the analysts the amount of risk that the company is ready to take. If you are estimating the sale volumes expected in a new area, how much can those estimates be away from the real value to be safe?
Share with the analysts what you consider to be reasonable probabilities of taking wrong decisions from the results of the analysis. Analysts can translate these probabilities into potential financial losses and use them to estimate the amount of data needed for analyses (see below).

From all this information and for each need, analysts will suggest analytical procedures with precise estimations of the amount of data needed.

At the end of the present procedure, you will be able to calculate the cost and duration of each analysis to address the different needs which will directly impact their feasibility.

At the end, you will have a good estimation of the potential benefits of addressing each need at the same time of the feasibility of associated analyses to prioritize which of these needs should be addressed with your tight budget 😊

Do your data analysts learn enough about your business environment?

Thu, 16 Jun 2022 15:33:33 +0200

In many aspects of statistics, field expertise must enter the analytical process to generate robust and reliable information. For instance, modeling potential causes of variations of a metric of interest (e.g., daily sales, price elasticity) can strongly benefit from inputs by field experts (e.g., sale assistants, product managers). This is especially true, when the size of the sample is close to the number of potential explanatory variables.

For instance, we might be interested in the customer characteristics that explain how many beauty products they buy on our platform.

Let assume a first situation where one of our field expert shares with our analyst his intuition about "weather" and "sex" influencing customer cosmetics purchases. If our analyst follows his indications, he will test the different models that include both variables as potential causes and will not consider other variables present in our customer database. If there is a causation link between those two variables and the cosmetics purchases (and no other variables are of strong influence), some of these models will show good accuracy, and allow drawing reliable conclusions about potential causes influencing the number of cosmetics bought.

Now, let say that our analyst is left to the job of fitting the model without any input from a field expert. Because he does not know which variable is expected to influence cosmetics purchases, he will test all models including the weather, the customer sex, and all other variables present in the database (e.g., sock purchases). Let assume again that these other variables do not influence the shopping behavior which interests us.

Including in the model all those additional variables will likely end up with detection of spurious effects. In other words, our results will support that some variables have a significant effect on the customer behavior, even if this is not the case. One of the reasons is that the effects of some variables might be biased away from zero in the sample. For instance, despite that there is no link among the sock and cosmetics purchases, we might have sampled persons which wrongly give the impression that a customer who bought socks in the last month buys fewer cosmetics now. Because this effect is not real, if we had the opportunity to redo the sampling, this effect is more likely to not be detected again. Unfortunately, in most cases, we have access to only one sample and there are no ways to know which parameter of the model is biased. In addition, the presence of these spurious effects will lead to an overestimation of the precision of the model.

To avoid this problem, field experts should express their a priori knowledge about the variables that they believe to be of some influence (sex and weather in the example above). This information will help analysts to define which models are reasonable to test among the many conceivable. In the example of the cosmetic purchases, the analyst who received field-expert input tested the models with weather and sex as explanatory variables without socks. This strategy avoided the selection of models with spurious effects, and which provided information which cannot be generalized beyond the sample used.

That being said, one might be interested to take the risk of having those spurious effects to be present in the models if they can afford future investigations to confirm their effects or rule them out.

Sign up to receive the next article!

Mon, 23 May 2022 15:59:25 +0200

What do we plan to share with you:

As a company offering project support and tailored courses around analytics, we will regularly share short articles. Those will aim to help you to maintain the best standards in your daily practice of analytics!

We hope you will find them useful, and do not hesitate to send feedback.