@conference {352, title = {Identifying Facet Mismatches In Search Via Micrographs}, booktitle = {International Conference on Information and Knowledge Management (CIKM)}, year = {2019}, abstract = {E-commerce search engines are the primary means by which customers shop for products online. Each customer query contains multiple facets such as product type, color, brand, etc. A successful search engine retrieves products that are relevant to the query along each of these attributes. However, due to lexical (erroneous title, description, etc.) and behavioral irregularities (clicks or purchases of products that do not belong to the same facet as the query), some mismatched products are shown in the search results. These irregularities are often detected using simple binary classifiers like gradient boosted decision trees or logistic regression. Typically, these binary classifiers use strong independence assumptions between the samples and ignore structural relationships available in the data, such as the connections between products and queries. In this paper, we use the connections that exist between products and query to identify a special kind of structure we refer to as a micrograph. Further, we make use of Statistical Relational Learning (SRL) to incorporate these micrographs in the data and pose the problem as a structured prediction problem. We refer to this approach as structured mismatch classification (smc). In addition, we show that naive addition of structure does not improve the performance of the model and hence introduce a variation of smc, strong smc (s2mc), which improves over the baseline by passing information from high-confidence predictions to lower confidence predictions. In our empirical evaluation we show that our proposed approach outperforms the baseline classification methods by up to 12\% in precision. Furthermore, we use quasi-Newton methods to make our method viable for real-time inference in a search engine and show that our approach is up to 150 times faster than existing ADMM-based solvers.}, keywords = {collective classification, defect, probabilistic soft logic, search, statistical relational language, structured prediction}, author = {Sriram Srinivasan and Nikhil S Rao and Karthik Subbaian and Lise Getoor} }