Business Data problem : Strategic market intelligence
how to stay ahead of the competition …
Problem summary
My organization wants to know which companies are similar to each other to help in identifying potential customers of a SAAS software solution (e.g. Salesforce CRM) in various segments of the market. The Sales Department is very interested in this analysis, which will help them more easily penetrate various market segments.
Solution Summary
The Analytics Department developed two unsupervised algorithm to classify companies based on how their stocks trade using their daily stock returns (percentage movement from one day to the next). This analysis will deliver value to the stakeholders to determine which companies are related to each other (competitors and have similar attributes)
Stock price analysis
We have stock prices for every stock in the SP 500 index, which is the daily stock prices for over 500 stocks. The data set is over 1.2 M observations.
Skree plot : optimum number of segments
The skree plot is an cutting-edge plot obtain from K-Means ML technique that helps to determine in how many clusters we can gathered our overall data set based on the user-matrix that we provided to the algorithm.
I used this technique here and the result shows that we can segmented the SP500 in 10 subgroups based on the daily stock price (nota bene : I made a filter to get the data starting on 2018).
SP500 companies Segmentation : 2D projection
I used here a combination of 2 algorithms : K-Means and UMAP to assign each company to its clusters. The result is here (below). I get an interactive version of this plot on rpubs website (https://rpubs.com/dimsu/market_intelligence)
Conclusion
The solution I provided to my boss is a cutting-edge report that gives value to stakeholders.
The repository of this project i son my github channel, where you can find the .pdf report (link below)
