Building an ML-Powered Transaction Classifier with Retraining and A/B Testing
Every month I download a CSV from my bank with all our household transactions. Each one needs a category: groceries, fuel, mortgage, subscriptions, insurance. With 200+ transactions per month across […]...
Five Architectures for Time Series Forecasting with Large Language Models
Large Language Models are increasingly being applied to time series forecasting. Not as chatbots, but as prediction engines that leverage the pattern recognition capabilities of transformer architectures to forecast numerical […]...
Local Audio Transcription with MLX Whisper and AI agent API on Apple Silicon
I attend a lot of meetings. Some are in-person, some remote, but almost all of them benefit from having a transcript and summary afterwards. Commercial transcription services work well, but […]...
Ten Terminal Tools That Changed My Data Science Workflow
Most data scientists spend their days in Jupyter notebooks and IDEs. But a surprising amount of daily friction happens in the terminal: navigating to project folders, searching through code, inspecting […]...
The Transformative Role of Large Language Models in Time Series Forecasting
Time Series Forecasting (TSF) is crucial in data science for predicting future values from historical data. Traditional methods often struggle with complex, variable data, but Large Language Models (LLMs) offer new capabilities. LLMs excel in capturing intricate patterns and handling unstructured data like text, enhancing forecast accuracy. They are...
From Hypothesis to Insights: A Step-by-Step Guide for people interested in Machine Learning Engineering
In this article I describe a series of steps that I learned through study and practise, each crucial for the success of ADSAI project. The steps are based on best […]...