Data Science Meetup in Beer Sheva

Agenda:

18:00 - 18:30
Networking and Refreshments

18:30 - 19:15
Shiri Gaber, Senior Data scientist @ Dell EMC Israel

Hard Disk Drives (HDD's) sometimes fail with no apparent reason; some SMART (Self-Monitoring, Analysis and Reporting Technology) attributes present strong correlations with drive failures, yet a drive may also fail without (supposedly) any previous indication. Most of the host systems today utilize alert-methods which are reactive by nature- a drive is indicated to fail when some SMART attribute exceeds its vendor defined threshold for valid operation. This approach does not take the cross correlation between different attributes into account and the fact that thresholds vary across different vendors. Machine learning has spanned in recent years over many fields. We, at Dell\EMC have been using ML techniques to predict disk drive failures from time-series telemetry. In this session, we will describe our journey and techniques we used for disk drive failure prediction and our findings.

19:15 - 20:00
Aviv Rotman, Algorithm Engineer @Taboola

Deep Modeling for Content Recommendation:
Taboola is powered by a recommendation engine that aims to match users with content that suits them most out of a langpool of over a million possible recommendations. Deep Learning models have been gaining increasing attention in the recommendation systems community, replacing some of the traditional methods. The sparse nature of the problems in this domain and the different types of inputs offer unique challenges for feature engineering and architecture planning, in order to balance between memorization and generalization.

In this talk, we will discuss our journey to apply DNN modeling techniques for the purpose of predicting click through rate in our content recommendation system. We will deep dive into some common (and some not so common) architectures and discuss how they come into place in our problem. Specifically, we will talk about building neural networks with multiple input types (click history, text and pictures); feature engineering in the deep learning era; Tradeoffs between deep models, shallow models and the combination of the two; and other tips regarding network architectures.