I worked on the project Carbon Dashboard, which provides granular insights and analysis of carbon emissions across buildings—developed a Time Series Model using Machine Learning to predict the attendance of people, to allow better planning, reducing the wastage of resources and carbon emission. Used features like trend, seasonality and correlation for tuning the model. Tech stack used: PySpark, Python, SQL, Databricks, PowerBI and Azure services. I worked on this project during my internship at Microsoft. The project achieved 2nd place globally in the domain Hack for Sustainability at the Microsoft Global Hackathon 2020.
Built deep learning models for Monitoring the Health of Building Structures which allows keeping track of structural damage using features like inter-story drift ratio and data from accelerometer signals. Used CNNs on simulated accelerometer data for classifying structural state based on damage. This can help address vulnerable structures and prevent the loss of life and property after a natural disaster. Worked on the project during my internship at CEERI Pilani. GITHUB
This project aims to predict consumer behaviour using brain wave measurement technology and machine learning. Processed the collected brain data‑EEG signals using MATLAB EEGlab toolkit. Developed a Machine Learning Model in Python to predict consumer behaviour using classification algorithms like K‑ Nearest Neighbors and Random Forest on the processed EEG data. This project was done under the guidance of Prof. Bharat Deshpande, BITS Pilani, K K Birla Goa Campus. GITHUB.