Gauri Kapse
Data Analyst with 3 years of experience and a master's degree in Analytics from Georgia Institute of Technology. UC Berkeley alum.
I work within the Marketing Strategy, Planning and Insights team within the broader Marketing team at talabat—the Middle East's largest food delivery platform—to provide strategic recommendations on spend efficiency, marketing initiatives and product decisions to regional and local teams.
Previously, at Commutatus, I supported the operational needs of 13 SMEs in various industries across the EMEA by providing analytical insights and data-driven recommendations.
Portfolio
Simulating Vaccine Distribution Strategies in an Epidemic
I simulated a short-term epidemic spread in Python to assess the impact of mitigation strategies like social distancing and vaccinations. All output analysis was conducted in R.
A Chatbot to Answer Questions about Books
I built a chatbot to answer questions about my most-referenced books using the LangChain framework in Python! The UI is built with gradio and is still a work-in-progress.
Building an NLP Powered Legal Text Summarizer
The Indian Central Government encourages ministries to place proposed legislations in the public domain for 30 days prior to making any decisions. During this period, anyone can provide feedback on the proposals. We worked with a non-profit, Civis, to leverage AI to summarize these proposals for the general public, and improve readability and access.
Read part 1 and part 2 of a recap of our efforts on Medium*.
* Articles co-authored by me and my colleague, but Medium doesn’t allow multiple authors.
Identifying Brain Proteins Critical for Learning in Mice with Down Syndrome
An attempt at replicating the results of the 2015 paper “Self-Organizing Feature Maps Identify Proteins Critical to Learning in a Mouse Model of Down Syndrome,” using a combination of non-linear dimensionality reduction and spectral clustering. The authors of the original paper have used self-organizing feature maps (SOM).
