I was invited to give a talk at the SIGIR Workshop On eCommerce 2019 but unfortunately, I am not attending SIGIR this year. Instead I wrote down some thoughts on interesting
problems, ideas and challenges in the e-commerce domain. Here they are:
- The vocabulary gap is still an open problem. People refer to products in different ways that products are described in the catalogue. Neural networks, learning to rank, query intent engines are all important. Our experience at 904Labs shown that a query intent engine that boosts specific product categories given a query, boosts our learning to rank system by more than 16% in additional revenue. These results suggest that effective initial ranking is very important for effective learning to rank. To this end, we foresee an increasing interest in methods that can re-rank the entire collection and not only the top-N documents. This is particularly important for larger shops with large inventories (> hundred of thousands of items) where a query can return hundreds of items, and only the top few are re-ranked.
- E-commerce search is as much as about exploration as it is about finding the best match. From our experience at 904Labs, we see a large fraction of queries to revolve around categories, or combinations of categories, e.g., “red shoes”, “kitchen tables”, “dvd players”, “ebooks for 12 years old”. This type of queries go beyond our typical search and require understanding the query and generating a list of recommended relevant items. This proposition is supported by the surprising effectiveness of sorting by popularity; the most popular items for a query are potential good candidates for this “recommendation list” that the user is looking for. Back to query understanding of this type of exploratory queries, one would think that natural language processing can help here but in the e-commerce setting, queries are very short and any language analysis falls short. An open question here is how can we go from these broad queries to a good set of recommendations? A natural way is devise a hybrid system of search and recommendations: We fire the query to a search system and then we take the first few items as seed to a recommender system for getting similar items. Or a system that transforms a query to an image (think AttnGAN or similar) and each product to an image and then rank documents by their image similarity to the query’s–the image representation may constraint the latent space, abstract the language of the query and that of the document and be able to capture semantics that are otherwise difficult to encode in textual form. The image representation of queries and documents also offers explainability when it comes to explaining the rankings of the system; which is becoming increasingly quite important in machine learning-based systems.
- Evaluation metrics in e-commerce. There several directions here that we need more work. First, the e-commerce setting is a conjunction of exploratory search, typical search, and recommendations. Using the standard IR precision and recall measures for e-commerce may not tell us the entire story for how happy makes its users. We need to discover the aspects of a system that makes users happy for designing one or more metrics for evaluating search and recommendation systems. These metrics should also correlate well with revenue but also with customer loyalty (measured in returning customers and in shortening the time between returns). Such a metric (or a multiple of metrics) will then allow us to run offline experiments and make predictions on revenue, which is the main KPI that systems are evaluated in production for most e-commerce business.
Extra tip: we found that boolean scoring may be on par or outperform tf.idf or BM25 scoring in the e-commerce domain, it’s worth checking its effectiveness on your own data 😉
On 31 May, I was invited to give a talk at TECH Talks in Amsterdam. TECH Talks is a new meetup organized by Techloop.io, a new way for matching jobs and talent in IT. My talk revolved on how we built an e-commerce focused search engine using machine learning (or as most people know it, A.I.). The meetup had a great start with more than 200 registered people and more than 100 people showed up; the room at TQ was at its maximum capacity! The audience was diverse with a nice mix of frontend, backend , senior and junior engineers, and also people from other disciplines who are interested in keeping up with latest developments in IT and e-commerce. Techloop and TQ were great organizers providing a great atmosphere (pizza and beer, included) facilitating great chats and networks afterwards.
You can see the video of the talks here (mine is the first after the introduction by Techloop):
The slides of my talk are here:
European Conference on Information Retrieval (ECIR) is a annual European scientific conference around bhe topics of search engines, recommender systems, text analytics, user modeling, and evaluation. This year ECIR was held in Grenoble, France. With more than 250 attendants and 4 days packed with tutorials, workshops, research, and industry talks, it was a great place to be to get updated with the latest and greatest about search engines.
The theme of this year’s Industry Day was to bring lessons learned from industry to academia. What are differences when developing a research algorithm and when we bring to practice? These lessons could inspire and inform our fellow academics for the challenges practitioners face when bring these algorithms to production.
In my talk I touched upon a bunch of challenges we’ve faced at 904Labs and how we came about to solving them. Open questions revolve around online learning to rank algorithms, delayed feedback, design of new metrics to avoid embarassing results, and the importance of investing in an evaluation platform. At 904Labs we have come a long way and we have working answers for these questions, however, as these questions are particularly difficult to answer, I’ve invited people to drop me a note with ideas, if they are interested. I’ve already got some nice feedback, and I hope to see more research on these areas in the near future!
Below are some tweets from my talk.
I was happy to be invited at Frankfurt Data Science meetup to talk about data science, meetups, and how to build a data science-oriented startup. The event was held at Frankfurt School on March 1st, 2018. In my talk I gave an overview of the meetup scene in Amsterdam, briefly presented Amsterdam Data Science and its activites, and then I shared my experiences on founding and developing 904Labs, before I delved into one of my favorite topics: machine learning and search.
It was a packed room, with more than 200 registered people for the event, and the talk was broadcasted live on YouTube. There will soon be a video, which I will share here. The audience was from diverse backgrounds, and I enjoyed the interactions very much. I was happily surprised by the professional organization of the event, and the ambition for making Frankfurt one of the leading centres in data science in Europe. All the best to the organizers and I hope to see more collaboration on data science between Frankfurt and Amsterdam in the near future!
The talk is online on YouTube (thank you Frankfurt Data Science for making this happen!):
Emakina, one of the largest web agencies in Europe, works with internationally acclaimed brands on their branding and electronic presence. To keep their customers ahead of the curve, Emakina has recently started a series of meetups where experts in a wide range of fields come and talk about the latest developments in their field. The last meetup was held last Thursday, 8 February 2018, and with the topic: “A.I. for Commerce”, three talks were scheduled: one from Emakina, one from 904Labs, and one from Salesforce.
In our talk, I described the importance of search in e-commerce by giving examples of failed searches in a number of settings, from finding advertized items using onsite search to mobile search. I followed by with why people choose Amazon to start their product search and highlighted that 54% of them choose Amazon because of their great search functionality–that is the reason number five for people to go to Amazon. Then, I explained why optimizing the ranking manually is close to impossible for humans by laying out the insane amount of options available and enumerating the search space (which can be at millions of millions of choices). With this as foundation, I talked about machine learning and the particular type of machine learning that we use at 904Labs for optimizing search rankings in real-time. I followed up with describing our query intent engine, which is powered by 904Sense, and our automatic synonym extraction engine. In my conclusions, I re-iterated that A.I. for Search can boost search-driven revenue by 30% and that search is becoming part of platforms. In this angle, it is important for online retailers to test the claims of their vendors by doing A/B tests before they opt in for a solution.
I was happy to be invited at the Amsterdam City A.I. Event on December 11, 2017. My talk revolved around our experiences at 904Labs in building a A.I. focused company. It was fun to be among A.I. enthusiasts and to see that people identified with our experiences–which means that we are on good track!
The talk is online on YouTube (clicking the link will start at my talk):
Below are some tweets from the event: