Glad you stumbled upon my webpage! I’m a 4th-year Statistics and Computer Science student @UWaterloo in Canada, passionate about delving into data science, machine learning, and artificial intelligence.
I am Aamodit Acharya, a 4th-year Statistics and Computer Science student at the University of Waterloo, studying from 2021 to 2026. My passion for data science ignited when I began watching Formula One and other sports, realizing how invaluable numbers are in crafting efficient strategies and understanding the bigger picture. I started my coding journey on my robotics team, where I began learning programming. I later participated in a local hackathon where I helped create a parking reservation app. Since then, I have worked for large banks and insurance companies in the pricing, analytics, and AI divisions.
I am actively seeking internships for Summer 2025 and Fall 2025 to apply my skills and contribute to impactful projects in data science and machine learning. I would love to get in touch.
Currently, I'm: Building my own PC and binge-watching the early Fast and Furious movies.
Developed a Python and Streamlit app using cosine similarity with scikit‑learn to recommend games based on IGDB API data, enhanced with seaborn visualizations.
Python, scikit‑learn
Built an image captioning model in Python using CNNs for image feature extraction and RNNs (LSTMs) for generating text captions, leveraging PyTorch to construct and train this multimodal architecture.
Python, PyTorch
Conducted a comparison of Kendrick Lamar and Drake’s song popularity in R using k‑Nearest Neighbors (kNN) classification and exploratory data analysis to analyze play distributions and distinct artist features.
R, k-Nearest Neighbors
Modeled GameStop (GME) stock volatility in R with linear regression, influence metrics, and robust regression (using gradient descent) to address outliers and highlight influential trading days.
R, Robust Regression
Assessed Edmonton Oilers’ goal‑scoring patterns in R with Poisson‑based MLE and MDE for goal distribution, applying the Horvitz‑Thompson estimator to evaluate bias, variance, and MSE in home vs. away goal averages.
R, MLE, MDE, MSE and Horvitz‑Thompson
Currently working on a sales forecasting model using the Walmart Kaggle dataset and XGBoost in Python, leveraging time‑series decomposition, hyperparameter tuning, and cross‑validation to predict sales trends and support strategic business insights.
Python, XGBoost