Contributed by: Pavan Kumar
Pavan Kuman is currently working for Citrix as Team Lead BI. Read further to learn about his journey with Great Learning’s PGP Data Science and Business Analytics Course in his own words.
I have done my Bachelor of Engineering in Information Science from Coorg Institute of Technology. I have a total of 12 years of experience in Dot Net Technology, MSBI, and Tableau. I have been working with Citrix for the last 5 Years on MSBI and Tableau. I had a very high-level knowledge of Data Science and was always interested in working with Data and finding insights.
Fortunately, after I joined the DSBA course with Great Learning, I moved to a new team that purely focuses on Analytics and Data Science projects. Because of this course, I have gained a lot of confidence, and I can contribute my knowledge and experience to multiple projects.
One of many projects that I am working on is “Customer Profiling.” The confidence and knowledge that I got from Great Leaning has helped me build a Customer Profiling model using the Clustering and RFM Model. Our company Citrix is an American multinational software company that provides server, application, and desktop virtualization, networking, SAAS, and cloud computing technologies. We have customers across the world. We had a Customer Churn and Customer Growth analytics project which shortlists customers at risk of Churn. These models were giving us a big list of customers at risk of Churn.
We have limited numbers of CSM (Customer Success Managers) who would work along with these customers at risk to find any roadblocks or improve the service. So, we can retain those customers. Because the list of customers at risk was high, it is impossible for our CSM to work with each customer.
Even after finding the customers at risk, we were unable to act effectively with each customer as the number of customers at risk was high. Because of this, we were losing many customers and hence losing a large part of revenue. I used Python, Tableau, and MSSQL to build Customer Profiling or Customer Segmentation.
Mainly the confidence that I have gained and the python language that I have learned have helped me build a Customer Profiling Model using clustering and RFM model. I was able to segregate a list of customers to different segments based on their previous transactions and help identify high-profit customers over low-profit customers.
I build a model using clustering and RFM model, thus identifying high-value customers over low-value customers. This reduced number of customers to concentrate first and helped CSM to target high-value customers and increase revenue with the same effort and bandwidth.
This has been a very valuable enhancement that helps us identify:
- Best overall customers
- Potential Valuable customers
- Find customer group who could contribute to the churn rate
- Customers who could be retained
- Find a customer who is likely to respond to engagement campaigns
This exercise helped me realize how things that I am learning can be used in my current role. It helped me to self-assess my skills before and after joining the DSBA program. I realized that I was on the right track, and this would be a turning point in my professional career.
