Towards Data Science

TDS Special Feature Expanding cities and a shrinking countryside Image from Unsplash, created by Louis Reed Are you a city dweller? You’re not alone! Our global urban population has reached … Read more

Deterministic trends vs stochastic trends, and how to deal with them Photo by Ali Abdul Rahman on Unsplash Detecting and dealing with the trend is a key step in the … Read more

How to “boost” your cyclical sales data forecast with LightGBM and Python Hierarchical time series forecasting (Image drawn by the author) Welcome to another edition of “The Kaggle Blueprints,” where … Read more

An overview of the research landscape combining structured and unstructured knowledge in NLP Photo by Billy Huynh on Unsplash This post is based on our AACL-IJCNLP 2022 paper “A Decade … Read more

If you don’t have real data, you got to fake it! Photo by Leif Christoph Gottwald on Unsplash In the world of data analytics, getting your hands on a good … Read more

From a digital elevation model to a 3D mesh Photo by Planet Volumes on Unsplash 3D meshes can be used to represent geographic data such as terrain, buildings and other … Read more

Mastering Time Series Forecasting with Machine Learning How your choice of loss function can make or break your time series forecasts Photo by Dan Asaki on Unsplash In this post … Read more

How to reduce the offline-online evaluation gap A recommender system jumping through the offline-online evaluation gap (AI-generated image) In this tutorial, I will give some rationales about why one should … Read more

A method for well-distributed approximation of the Pareto front Image generated by author with DALL-E by OpenAI Multi-objective optimization is a critical area of research that has wide-ranging applications in … Read more

Test Effectiveness of any Treatment over Time with PCA Photo by Raul Petri on Unsplash The standard, presented in the literature and adopted at large scale by companies, to study … Read more

Creating the artifacts and deploying the model on the cluster In part 1, we learned how to use terraform to set up and manage our infrastructure conveniently. In this part, … Read more

The need for proper validations and good datasets, objective and balanced, and that predictions be useful in realistic scenarios. Photo by Tingey Injury Law Firm on Unsplash Recent research in … Read more

Why causing your model to fail is the best thing you can do Photo by Michael Dziedzic on Unsplash When developing a new model or algorithm, it is tempting to … Read more

Learn How To Efficiently Write Data To Parquet Format Using Pandas, FastParquet, PyArrow or PySpark. Photo by Dominika Roseclay In today’s data-driven world, efficient storage and processing of large datasets … Read more

We use table variables in DAX all the time. But what when we need to calculate intermediary results and reuse them later in a DAX Measure? This challenge sounds easy, … Read more

NLP | MULTIMODALITY | CHAIN OF THOUGHTS | The world is not only text: How to extend the chain of thoughts to image and text? photo by Giulio Magnifico on … Read more

Boost your Python skills with this comprehensive class reference Image by Lukas Bieri on Pixabay When it comes to classes, many Python developers struggle, for a lot of reasons. Firstly … Read more

How minor modifications can make a major difference to the communicative power of your visualizations Photo by Mohamed Hassan on Pixabay Look at that poor guy above. He’s been grinding … Read more

Start storing models, parameters, pipelines, data and plots changing only one parameter Photo by Hans Reniers on Unsplash Introduction The MLflow Tracking component is an API and UI for logging … Read more

Photo by Kampus Production from Pexels: https://www.pexels.com/photo/a-judoka-throwing-an-opponent-to-the-ground-6765024/ Using pose estimation with mediapipe to track Jiu Jitsu movements Brazilian Jiu-Jitsu is a martial art that has been getting a lot of … Read more

Most common hyperparameter optimization methodologies to boost machine learning outcomes Photo by Jonas Jaeken on Unsplash Usually the first solution that comes to mind when trying to improve a machine … Read more

A guide on how to make a customized commuter’s map of your home city using data science and Google Maps API Last year I got a job in Massachusetts at … Read more

Development of a machine learning model for materials planning in the supply chain In today’s rapidly changing environment, one of the most critical challenges facing companies is the ability to … Read more

Thanks to PCA’s sensitivity, it can be used to detect outliers in multivariate datasets. Photo by Andrew Ridley on Unsplash Principal Component Analysis (PCA) is a widely used technique for … Read more

How to adjust CATE to consider costs associated with your treatments Photo by Remy Gieling on Unsplash Getting customers to come back to your business is hard. In the age … Read more

What happens and what you can/can’t do when merging evolutive DataFrames Photo by McDobbie Hu on Unsplash In the last post, we covered the transaction log and how to keep … Read more

Raw insights from IBM’s biggest transformation projects Legacy Waterfall and V-Models of software development rely on heavy upfront time investments to specify solutions, integrations or features, usually leading to extensive … Read more

Introduction to Predicting Treatment Effects on Recipients of Marketing Campaigns Image by geralt @ pixabay.com Imagine that you are responsible for selecting the customers in your company who should receive … Read more

Opinion The contribution of the AI Act and its worldwide impact Photo by DeepMind on Unsplash In mid-2021, the European Commission proposed a new EU regulatory framework on Artificial Intelligence … Read more

The basic structure of a flask application to allow for modular development Photo by KOBU Agency on Unsplash A Data Science workflow often involves the use of notebooks and python … Read more

How to train and validate ML models on multioutput datasets with minimal coding effort Photo by Victor Barrios on Unsplash Introduction The standard machine learning tasks everyone is familiar with … Read more

Opinion Having a hammer and seeing everything as a nail Photo by Sergei Chuyko on Canva Recently, I had an opportunity to meet with a data science team from a … Read more

Text everywhere! Since the Internet was spread around the world, the amount of textual data we generate everyday is ginormous. Only textual messages sent everyday, it is estimated that there … Read more

100+ new metrics since 2010 Image from Pixabay An evaluation with automatic metrics has the advantages to be faster, more reproducible, and cheaper than an evaluation conducted by humans. This … Read more

Data curation in computer vision lacks standardization, leaving many practitioners unsure how to do it correctly. We summarized some of the most common approaches. Where to start with data curation? … Read more

Opinion Qualitative methods, data manipulation, and media sources — as well as a detailed look into how numbers can lie Photo by Laurenz Kleinheider on Unsplash Much of the craze … Read more

TUTORIAL Explore the mysteries of quantum computing! Source: Stable Diffusion. Whenever I learn a new programming language or framework, I often find myself trying to program a game as a … Read more