Towards Productionizing Subjective Search Systems
This addresses the challenge of making subjective attributes searchable for users in e-commerce domains like jobs and travel, though it is incremental as it builds on an existing prototype with domain-specific enhancements.
The paper tackled the problem of enabling search over subjective attributes in e-commerce, which existing systems lack, by productionizing a subjective search prototype for Recruit Group, resulting in a 5%-10% overall precision improvement and over 90% precision on more than half of benchmark queries.
Existing e-commerce search engines typically support search only over objective attributes, such as price and locations, leaving the more desirable subjective attributes, such as romantic vibe and worklife balance unsearchable. We found that this is also the case for Recruit Group, which operates a wide range of online booking and search services, including jobs, travel, housing, bridal, dining, beauty, and where each service is among the biggest in Japan, if not internationally. We present our progress towards productionizing a recent subjective search prototype (OpineDB) developed by Megagon Labs for Recruit Group. Several components within OpineDB are enhanced to satisfy production demands, including adding a BERT language model pre-trained on massive hospitality domain review corpora. We also found that the challenges of productionizing the system are beyond enhancing the components. In particular, an important requirement in production-quality systems is to instrument a proper way of measuring the search quality, which is extremely tricky when the search results are subjective. This led to the creation of a high-quality benchmark dataset from scratch, involving over 600 queries by user interviews and a collection of more than 120,000 query-entity relevancy labels. Also, we found that the existing search algorithms do not meet the search quality standard required by production systems. Consequently, we enhanced the ranking model by fine-tuning several search algorithms and combining them under a learning-to-rank framework. The model achieves 5%-10% overall precision improvement and 90+% precision on more than half of the benchmark testing queries making these queries ready for AB-testing. While some enhancements can be immediately applied to other verticals, our experience reveals that benchmarking and fine-tuning ranking algorithms are specific to each domain and cannot be avoided.