Collaborative Trial: On Optimizing Recommendation Testing

Maoz Cohen | 09 Jun 2020 | Big Data

Tags: a/b testing, algorithms, big data, data, data science, Monitoring, performance, statistics, testing

Taboola is responsible for billions of daily recommendations, and we are doing everything we can to make those Read More...

‘Tis the Season: Fun with (Decision) Trees

Marina Gandlin | 18 Dec 2019 | Data Science

Tags: algorithms, data, data model, data science, machine learning, python

At Taboola, we work daily on improving our Deep-Learning-based content-recommendation model. We use it to suggest personalized news Read More...

Performing Exploration, Robin-Hood Style

Shaked Zychlinski | 11 Nov 2019 | Machine Learning

Tags: algorithms, data model, data science, deep learning, exploration, machine learning, neural networks

Our core business at Taboola is to provide the surfers-of-the-web with personalized content recommendations wherever they might surf. Read More...

Exploiting Multi-Categorical Features Using Deep Interest

Marina Gandlin | 04 Sep 2019 | Data Science

Tags: algorithms, big data, data, data model, data science, deep learning, machine learning, neural networks

At Taboola, our goal is to predict whether users will click on the ads we present to them. Read More...

Going Old-School: Designing Algorithms for Fast Weighted Sampling in Production

Shaked Zychlinski | 06 Jun 2019 | Big Data

Tags: algorithms, performance, production, real-time, sampling, uncertainty

If you happen to write code for a living, there’s a pretty good chance you’ve found yourself explaining Read More...

The Hitchhiker’s Guide to Hyperparameter Tuning

Yoel Zeldes | 14 Jun 2018 | Data Science

Tags: algorithms, data, data science, hyperparameter tuning

Now that more than a year has passed since our first deep learning project emerged, we have had Read More...

Using Word2Vec for Better Embeddings of Categorical Features

Inbar Naor | 25 Apr 2018 | Data Science

Tags: algorithms, deep learning, prediction, word2vec

Back in 2012, when neural networks regained popularity, people were excited about the possibility of training models without Read More...