Understand the key elements that power advanced recommendation engines — One of the most important types of models in recommendation systems at present is the two-tower neural networks. They are structured as follows: one part of the neural network (tower) processes all the information about the query (user, context), while the other tower processes information about the object. The outputs…

Many services feature ratings of objects: products, movies, applications, organizations on a map. How should these be accurately calculated? The question is not as simple as it seems at first glance. I won’t even touch upon important nuances such as dishonest manipulation of ratings, or the fact that reducing the…

Don’t let heuristics undermine your ML, learn to combine them — In today’s data-driven landscape, recommendation systems power everything from social media feeds to e-commerce. While it’s tempting to think that machine learning algorithms do all the heavy lifting, that’s only half the story. …

In recommender systems, you frequently encounter situations where you have access to ‘external embeddings.’ These are embeddings trained independent of the task at hand — like using BERT for text or a pretrained neural network applied to images. Users might also bring external information, perhaps from their activities on another…

Continuing from our post about linear models, today we’ll delve into a specific case — Sparse Linear Methods (SLIM). Here’s what sets this method apart: It’s simple. The model is interpretable, making it easy to debug. It’s quite efficient; the model trains quickly (though this depends on the problem size). …

Linear models are nearly the simplest tools in machine learning, but they shouldn’t be underestimated. They are remarkably adaptable, and their predictive power can be enhanced by utilizing good features. This post explores one of their applications in recommendations and draws an analogy with counters. Let’s start with the basics…

In recommendations and similar ML tasks, the use of counters as features is a popular approach. Examples include the number of times a user has clicked on documents from the same host or a document’s CTR (calculated using two counters — clicks and impressions). Often, composite keys for aggregation are…

A successful exam is one where you not only pass but also learn something new. More than a year ago, I interviewed at Microsoft. During one of the interviews, I was asked a question to which I didn’t respond very well. Even after hearing the answer, I didn’t grasp it…

The minimization of the sum of squares on a logarithmic scale inevitably causes some bias. I’d like to delve deeper into this statement I shared in my previous post. I’ll begin with an example from my personal experience. Once, I was involved in a project aimed at forecasting a certain…