Technical Blog
AI insights and customer stories
Before You Fix Your Data, Understand It.
A practical walkthrough of feature interpretation and sanity checks before training models on the Forest Cover Type Prediction dataset.
Kaggle Competition: Spaceship Titanic
Explored missing-value patterns and model pipelines for Kaggle's sci-fi classification challenge.
Bike Sharing Demand Forecasting
Forecasted hourly bike demand with time-aware validation and a focus on seasonality patterns.
Instagram Graph Analysis and Community Detection
Applied graph algorithms to map community structure and identify influential nodes in an Instagram dataset.
Lunar Landing Assignment
Trained a reinforcement learning agent with reward shaping to maximize stable, accurate landings.
Training AWS DeepRacer
Built a custom reward function to balance lap time with centerline stability in AWS DeepRacer.
Corporate Data Breaches and Narrative Disclosures
An undergraduate thesis examining how public firms adjust narrative disclosures after data breaches.
Master Thesis: Raw Material Forecasting of Industrias Duero
A collaborative master thesis on demand forecasting and supply chain optimization using ML and time-series methods.
Learning to Land with PPO
How Proximal Policy Optimization (PPO) learns to land a tiny spacecraft: task setup, key equations, intuition, and the hyperparameters that keep training stable.
An Attempt to Make Reinforcement Learning Simple
A conversational walk through reinforcement learning: the problem it solves, how the loop works, and why exploration matters.
From Prediction to Decision: A Gentle Introduction to Reinforcement Learning
A clear and visual introduction to reinforcement learning, and how it differs fundamentally from supervised and unsupervised learning.
Reinforcement Learning, Explained
A beginner-friendly introduction to reinforcement learning: the agent-environment loop, MDPs, policies, and the exploration tradeoff.