Practical AI AI for search at Etsy
Dec 23, 2019
Andrew Stanton, the product manager of search ranking at Etsy, shares his 15 years of experience in machine learning and search technology. He delves into how AI is transforming search in e-commerce, discussing the challenges of tailoring search for various handmade and vintage items. Andrew introduces neuroevolution, a method aimed at enhancing search algorithms, and emphasizes the benefits of using Rust programming for ML systems. He also shares insights on future trends in AI and its impact on search technology.
AI Snips
Chapters
Transcript
Episode notes
AOL Radio Show
- Andrew Stanton's first ML experience involved predicting listener tune-in times for an online radio show at AOL.
- This introduced him to linear regression and time series prediction.
Multimodal Deep Learning
- Multimodal deep learning helps analyze unstructured data like images and text descriptions.
- This is crucial for platforms like Craigslist or Facebook Marketplace, which lack structured product data.
Early Search Algorithms
- Early search algorithms relied on methods like TF-IDF and BM25.
- These statistical methods prioritize rarer tokens, assuming they contain more information.