ML-Driven Recommendation System
Building a personalized recommendation engine that delivered $500K annual revenue impact
Project Overview
[Read More]
Supply chain for server components using survival analysis, XGB embedding
predictive model for the live data of servers
For a major US technology company, the time it took for components, racks, and servers to go live from the moment they were ordered was taking several years, and the number of components required varied significantly and was difficult to estimate accurately. They needed a model to predict with precision...
[Read More]
Supply chain for pharmaceutical company
Solved using and gurobi based software and results presented using PBI
This was my first project at Accenture. Due to the pandemic, one of the world’s largest pharmaceutical companies wanted to optimize their vaccine distribution routes across the globe. The vaccines were delivered in different packages and formulations worldwide, with the USA being the principal market.
[Read More]
Sindy
Classificator using LASSO for neuronal clusters
My PhD director developed an elegant algorithm called Wave_clus, written in MATLAB, that clusters signals coming from electrodes in brain patients’ recordings to differentiate the activity from distinct neurons. However, the algorithm can’t automatically decide which “cluster” comes from a neuron versus noise.
[Read More]
Mercado Libre Challenge
Poisson regression to predict how much time it will take for stock to be sold
Some friends and I participated in a Mercado Libre (MELI) data science challenge focused on predicting the probability of inventory being sold after N days. This was my first time working on this type of project with e-commerce data. While we didn’t win, it was an incredibly valuable learning experience....
[Read More]