Raghav Raipuria

Capillus | Image Classification of a patch of human scalp & predict the number of hairs in 3 predefined ranges. Analyzed and preprocessed 600 images of 3 classes using OpenCV. Built Convolutional Neural Network Model (CNN) with transfer learning and got an accuracy of 76% in Keras, TensorFlow. Increased accuracy with pre-trained ResNet34 CBAM CNN architecture to 78% and also implemented Vision Transformer, MLP Mixer architecture to improve classification metrics by PyTorch. Trade Promotion Optimization | Optimize Business KPIs of store marketing by placing products at promotion. Generated new datasets by combining data from multiple source systems with SQL queries and performed feature engineering on data having 100+ columns using NumPy, pandas. Developed a mathematical optimization model using Gurobi in Python to find decision variables that result in an increase in Net Revenue by 8% & delivered one monitoring dashboard to track business KPIs in Tableau.

Created Machine learning & ANN models as an internal project of the company in Telecom, BFSI field. Automated scheduled run of code deployed in Kubeflow environment saved one day of effort weekly with regular code changes maintained in Git Repository and contributed to client project delivery. Trade Promotion Optimization | Optimize Business KPIs of store marketing by placing products at promotion. Generated new datasets by combining data from multiple source systems with SQL queries and performed feature engineering on data having 100+ columns using NumPy, pandas. Developed a mathematical optimization model using Gurobi in Python to find decision variables that result in an increase in Net Revenue by 8% & delivered one monitoring dashboard to track business KPIs in Tableau.

Designed self Api onboarding feature to add/update backend link of APIs with SQL query to remove dependency on deployment cycle and reduced two days of effort monthly in Java, Python, Git.