ideas and opinion on what kind of analyses needs to be done

Question

Hello Guys,

I have been given a task where I need to analyse the impact of all the products that were discontinued last year on the customers and sales? I work for a retail company which has 100s of stores in North America and my analyses needs to be "Qualitatively better than the regular BI".

I quote that because thats what I was asked to do. I am struggling to come up with ideas. What kind of hypothesis should I test. Or any Bayesian analyses that can be done. Any ideas within the realms of data science and machine learning is welcome.

I generally do my analyses using Jupyter Notebook and my skill set consist of SQL, Python including ML libraries like sklearn

Answer 1

It is a broad question and could have many answers. You can ask many questions and try to answer them based on your main business problem: "the impact of all the products that were discontinued last year on the customers and sales". For example:

• You can analyze a hypothesis that discontinuing a specific product was a good decision or a bad decision?
  • You can check the sale increase in similar not-discontinued products of the store to investigate if customers who used to buy the discontinued one still looking for it or not. You can build the null hypothesis and alternative hypothesis to analyze the impact statistically.
  • You can review customer calls/emails after discontinuing and analyzing the sentiment of the customer for this decision. It could be done using machine learning.

You have to generate questions and try to answer them using the data you have. It totally depends on how you define impact in your statement. After generating the questions, and finding answers, you can recommend some advice based on your results. For example, if you find out discontinuing the product was a bad decision, you can recommend to continue it again.