📌 Case-Study: Multilingual LLM for Questionnaire Summarization

🗂 Category:

🕒 Date: 2024-07-30 | ⏱️ Read time: 12 min read

An LLM Approach to Summarizing Students’ Responses for course Questionnaires in Hebrew, Arabic and English

📌 How To Log Databricks Workflows with the Elastic (ELK) Stack

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-07-30 | ⏱️ Read time: 9 min read

A practical example of setting up observability for a data pipeline using best practices from…

📌 Spatial Index: R Trees

🗂 Category: DATABASE DESIGN

🕒 Date: 2024-07-30 | ⏱️ Read time: 11 min read

Data-driven structures for spatial indexing If you have been following the Spatial Index Series, it…

📌 Shortest Path Algorithms: How to Use Data to Navigate and Optimize

🗂 Category: DATA SCIENCE

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

An Overview of Dijkstra’s Algorithm and Bellman-Ford Algorithm

📌 Can Generative AI Lead to AI Collapse?

🗂 Category: ARTIFICIAL INTELLIGENCE

🕒 Date: 2024-07-30 | ⏱️ Read time: 9 min read

AI eating its own tail: the risk of model collapse in generative systems

📌 Data Warehouse, Redefined

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-07-30 | ⏱️ Read time: 9 min read

Rethinking data warehousing: Why redefinition is necessary even beyond Modern Data Warehouse (MDW) and Lakehouse…

📌 A Practical Guide to Contrastive Learning

🗂 Category: DEEP LEARNING

🕒 Date: 2024-07-30 | ⏱️ Read time: 10 min read

How to build your very first SimSiam model with FashionMNIST

📌 Deploying dbt Projects at Scale on Google Cloud

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-07-29 | ⏱️ Read time: 13 min read

Containerising and running dbt projects with Artifact Registry, Cloud Composer, GitHub Actions and dbt-airflow

📌 How to Stand Out in Your Data Scientist Interview

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-29 | ⏱️ Read time: 9 min read

A tip from my experience hiring Data Scientists, which even seasoned professionals aren’t aware of

📌 Visualizing 3D Spatial Data With Pydeck

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-29 | ⏱️ Read time: 4 min read

How to create building model maps in Python

📌 Stable and fast randomization using hash spaces

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-29 | ⏱️ Read time: 8 min read

Generate consistent assignments on the fly across different implementation environments

📌 Navigating Data Science: B2C vs. B2B Analytics

🗂 Category: BUSINESS

🕒 Date: 2024-07-29 | ⏱️ Read time: 12 min read

How customer types shape data science roles and methodologies

📌 Hands on Career Path Modelling Using Markov Chain, with Python

🗂 Category: CAREER ADVICE

🕒 Date: 2024-07-29 | ⏱️ Read time: 14 min read

This is how I used basic probability to simulate career development

📌 Python Set Is Way Faster Than List, True Or False?

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-29 | ⏱️ Read time: 6 min read

Comprehensive performance comparison and discussion around data structure

📌 Isochrones in Python

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-29 | ⏱️ Read time: 4 min read

Highlighting walkability areas in Python

📌 Fine-Tune Llama 3.1 Ultra-Efficiently with Unsloth

🗂 Category: LARGE LANGUAGE MODELS

🕒 Date: 2024-07-29 | ⏱️ Read time: 14 min read

A beginner’s guide to state-of-the-art supervised fine-tuning

📌 Maximize Savings on Your Unused Fabric Capacities

🗂 Category: DATA ENGINEERING

🕒 Date: 2024-07-29 | ⏱️ Read time: 9 min read

Automate your Microsoft Fabric capacity state with Azure Logic Apps Disclaimer: This post will not…

📌 You Didn’t Conduct an A/B Test. You Can Still Simulate One Retrospectively.

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-29 | ⏱️ Read time: 17 min read

Modeling a synthetic (but high quality) control group as a baseline to infer whether the…

📌 A Simple Regularization for Your GANs

🗂 Category: MACHINE LEARNING

🕒 Date: 2024-07-29 | ⏱️ Read time: 17 min read

In 2018, I had the privilege of orally presenting my paper at the AAAI conference.…

📌 Was Michael Scott the World’s Best Boss?

🗂 Category: DATA SCIENCE

🕒 Date: 2024-07-29 | ⏱️ Read time: 17 min read

Sentiment analysis of ‘The Office’ TV series using SchrutePy, NLTK and Hugging Face Transformers

📌 Does Data-Driven Storytelling Need to Be Objective?

🗂 Category: DATA VISUALIZATION

🕒 Date: 2024-07-29 | ⏱️ Read time: 14 min read

Striking the balance between efficiency and engagement of your data-driven stories