📌 Document Parsing Using Large Language Models – With Code

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2024-07-25 | ⏱️ Read time: 17 min read

You will not think about using Regular Expressions anymore.

📌 Unit Disk and 2D Bounded KDE

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-25 | ⏱️ Read time: 14 min read

0. Introduction MonteCarlo Integration Numerical methods become essential when closed-form solutions for integrals are unavailable.…

📌 Handling Hierarchies in Dimensional Modeling

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-07-24 | ⏱️ Read time: 16 min read

Hierarchies play a crucial role in dimensional modeling for Data Warehouses. See my recommendations on…

📌 Improving RAG Answer Quality Through Complex Reasoning

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2024-07-24 | ⏱️ Read time: 31 min read

Showcasing the process for building a multi-hop retrieval system using DSPy and Indexify

📌 Forecasting US GDP using Machine Learning and Mathematics

🗂 Category: ECONOMICS

🕒 Date: 2024-07-24 | ⏱️ Read time: 17 min read

What can we learn from this modern problem?

📌 The Intersection of Memory and Grounding in AI Systems

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2024-07-24 | ⏱️ Read time: 8 min read

Understanding the 4 key types of memory, the methods of language model grounding, and the…

📌 Past is Prologue: How Conversational Analytics Is Changing Data Work

🗂 Category: DATA SCIENCE

🕒 Date: 2025-10-09 | ⏱️ Read time: 7 min read

The future of reporting will be about encoding the value proposition of a product into…

📌 How the Rise of Tabular Foundation Models Is Reshaping Data Science

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2025-10-09 | ⏱️ Read time: 13 min read

A turning point for data analysis?

📌 Python Poetry – The Best Data Science Dependency Management Tool?

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-30 | ⏱️ Read time: 8 min read

Poetry makes deploying machine learning applications a breeze – learn how!

📌 10 Data + AI Observations for Fall 2025

🗂 Category: DATA SCIENCE

🕒 Date: 2025-10-10 | ⏱️ Read time: 10 min read

What’s happening—and what’s next— for data and AI at the close of 2025.

📌 Dreaming in Blocks — MineWorld, the Minecraft World Model

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2025-10-10 | ⏱️ Read time: 11 min read

Explaining “MineWorld: A real-time and open-source interactive world model on Minecraft” in simple terms.

📌 Boost Your Data Science Job Hunt During Tech Layoffs, Part I

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-23 | ⏱️ Read time: 7 min read

With these 5 actionable steps

📌 Linear Programming Optimization: Foundations

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-22 | ⏱️ Read time: 12 min read

Part 1 – Basic Concepts and Examples

📌 What Is Causal Inference?

🗂 Category: STATISTICS

🕒 Date: 2024-07-22 | ⏱️ Read time: 13 min read

A beginner’s guide to causal inference methods: randomized controlled trials, difference-in-differences, synthetic control, and A/B…

📌 LangChain’s Parent Document Retriever – Revisited

🗂 Category:

🕒 Date: 2024-07-22 | ⏱️ Read time: 7 min read

Enhance retrieval with context using your vector database only

📌 Quantifying Burned Areas from Wildfires Using Satellite Imagery

🗂 Category: CLIMATE CHANGE

🕒 Date: 2024-07-22 | ⏱️ Read time: 9 min read

Determining the burned area in forests due to wildfires using Sentinel-2 images with Python in…

📌 You Don’t Need Matplotlib When Pandas Is Enough for Data Visualisation

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-22 | ⏱️ Read time: 6 min read

One line of code to plot data makes routine EDA jobs easier

📌 Python’s Parallel Paradigm Shift

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-07-22 | ⏱️ Read time: 13 min read

Exploring the performance potential of a GIL-free Python

📌 Advanced Data Modelling

🗂 Category: ANALYTICS

🕒 Date: 2024-07-21 | ⏱️ Read time: 16 min read

Data model layers, environments, tests and data quality explained

📌 How To Start Technical Writing & Blogging

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2024-07-21 | ⏱️ Read time: 8 min read

Why writing data science blogs changed my career.

📌 Let’s reproduce NanoGPT with JAX!(Part 1)

🗂 Category:

🕒 Date: 2024-07-21 | ⏱️ Read time: 8 min read

Part 1: Build 124M GPT2 with JAX. Part 2: Optimize the training speed in Single…