Jan 27 · 6 min read · Up to the previous post, the project was in a reasonably good state: data scraping worked, feature engineering was stable, models were trained and selected via MLflow, and offline inference behaved as expected. The system seemed to do what it was sup...
Join discussion
Nov 23, 2025 · 6 min read · Phase 4A was relatively smooth: I built a production-ready inference pipeline with modular preprocessing, caching, consistent schemas, and an MLflow-tracked model. Phase 4B was supposed to be the easy part: containerize the pipeline, wrap it in a Lam...
Join discussion
Nov 3, 2025 · 8 min read · In real-world ML, an accurate model is only the starting point. The real challenge is delivering reliable predictions at scale, ensuring that every step at inference, preprocessing, encoding, and feature alignment mirrors training. In this phase, I b...
Join discussion
Oct 14, 2025 · 11 min read · In real estate, extreme listings, both ultra-luxury and severely underpriced, can disproportionately influence predictions. These outliers, though rare, carry meaningful signals that must be preserved while keeping our model stable and robust. In thi...
Join discussion
Sep 30, 2025 · 10 min read · After scraping the Amsterdam Funda housing dataset, I noticed a handful of listings priced far beyond the rest of the market. These luxury outliers raised a central question: can models capture both the bulk of typical homes and these extreme, high-e...
Join discussion
Sep 4, 2025 · 8 min read · After setting up the project scope and tools last week, it was time to dive into Phase 2: Data Collection and Cleaning. This week was all about taking messy apartment listings and turning them into a structured dataset that’s ready for analysis and m...
Join discussion
Aug 24, 2025 · 4 min read · When I look at Amsterdam’s housing market, one thing is clear: it’s chaotic, fascinating, and full of patterns waiting to be uncovered. That curiosity sparked a question I couldn’t ignore: Can I predict the price range of houses in Amsterdam? With o...
Join discussion
Sep 29, 2024 · 21 min read · Here's the tree structure for the deployment of the Spring PetClinic app in Kubernetes: 1. Setup Kubernetes Cluster ├── Initialize control plane with kubeadm └── Add worker nodes to the cluster 2. Prepare Docker Images ├── Build PetClinic...
Join discussion
Aug 23, 2024 · 1 min read · Project Overview This project demonstrates the application of logistic regression to predict placement outcomes based on features such as CGPA and IQ scores. The goal is to build a predictive model that can accurately determine whether a student will...
Join discussion