We are so happy to announce the twelfth London Information Retrieval Meetup, a free evening meetup aimed to Information Retrieval passionates and professionals who are curious to explore and discuss the latest trends in the field.
This time the meetup will be a hybrid event, both in-presence and online!
The event will be structured with 2 technical talks, a Q&A session and a networking session after the talks.
IN PRESENCE MEETUP
Location: Gladwin Tower, nine elms point sw8 2fs London
Date: 30th March 2022 | 6:00-8:00 PM (GMT)
Date: 30th March 2022 | 6:15-8:00 PM (GMT)
Building an Open-source Online Learn-to-rank Engine
Relevancy is subjective. Same items in search results for a “jeans” query may have a completely opposite value for you and me, as we’re different in sizes, shapes, and tastes.
But leveraging past visitor behavior for LTR tasks often becomes a not so easy data engineering challenge when you want to use complex ML features in your ranking. Implementing crazy things like sliding window counters, per-item conversion+CTR rates, and customer profile tracking, working both online and offline – you need a whole team of DS/DE/MLE people and a lot of time to glue things together!
We got tired of reinventing the wheel of LTR again and again, and present you Metarank, an open-source personalization service handling the most typical and complex data+feature engineering tasks. It listens for an event stream describing your visitor behavior, maps it to most common ML features, and reorders items in real-time to maximize the goal like CTR. All you need is a YAML config and a bit of JSON I/O.
ML Engineer at Findify, working on search personalization and recommendations. A pragmatic fan of functional programming, learn-to-rank models and performance engineering.
Software engineer in the past, switched tracks to work closer with customers and product. Has multi-year experience of communicating with customers to understand what they really want and translating this information to engineers as a Head of Product.
How to Cache Your Searches: an Open source Implementation
Caches are used in IT systems to store data in dedicated structures for fast access so that future requests can be served faster. They are an effective tool to store the query results and speed up future query executions in information retrieval systems.
An open-source system like Apache Solr uses three different caches: queryResultCache, filterCache, and documentCache.
In this talk, we will focus on queryResultCache and filterCache and we will see, through practical examples, how they are used to handle different types of queries.