This project looks at the sales pattern of a product category in a retail store, using the store’s transaction dataset and identifying customer purchase behavior, to generate insights and recommendations.
This project comprises of 3 tasks:
We analyze the store’s transaction dataset and identify customer purchasing behaviors to generate insights and provide commercial recommendations.
There are two important datasets in this task, chips sales and customer data. The task is to carry out exploratory data analysis in order to extract insights about the purchasing behavior of different customer groups. We want to then use those insights to formulate strategies to help the store increase chip sales.
Below is the outline of our main tasks along with what we should be looking for in the data for each.
Examine transaction data – look for inconsistencies, missing data across the data set, outliers, correctly identified category items, numeric data across all tables. If we determine any anomalies we make the necessary changes in the dataset and save it. Having clean data will help when it comes to the analysis. Examine customer data – check for similar issues in the customer data, look for nulls and when we are happy we merge the transaction and customer data together so it’s ready for the analysis.
Data analysis and customer segments – in the analysis we make sure we define the metrics – look at total sales, drivers of sales, where the highest sales are coming from etc. Explore the data, create charts and graphs as well as noting any interesting trends and/or insights you find. These will all form part of the report.
Deep dive into customer segments – define recommendation from the insights, determine which segments should be targeted, if packet sizes are relative and form an overall conclusion based on the analysis.
We extend our analysis from Task 1 to help us identify benchmark stores that allow us to test the trial store layouts' impact on customer sales.
For this part of the project we will be examining the performance in trial vs control stores to provide a recommendation for each location based on our insight. There are 3 trial stores that have gone through a 3-month trial period with modified store layouts.
Below are some of the areas we focus on:
Select control stores – explore the data and define metrics for the control store selection – think about what would make them a control store. Look at the drivers and make sure we visualise these in a graph to better determine if they are suited. For this piece it may even be worth creating a function to help it.
Assessment of the trial – this one should give us some interesting insights into each of the stores, check each trial store individually in comparison with the control store to get a clear view of its overall performance. We want to know if the trial stores were successful or not.
Collate findings – summarise the findings for each store and provide an recommendation that we can share with the store, outlining the impact on sales during the trial period.
Use analytics and insights from Task 1 and 2 to prepare a report for the client(the retail store).(This document is not included in this repo.)