Implementation of a New Ranking Factor for Matching a Product Image to a Query

Student: Saidakbar Gaziev

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2024

Users often make purchasing decisions based on the appearance of products. Therefore, it has been suggested that Products Search results in which product images better match the search query could improve important business metrics of the service. In this project, we have implemented a new ranking factor that expresses the correspondence of the product image to the query. The paper describes applied for the computing image and text embeddings neural networks, their integration into backend services, the calculation of the new factor in runtime, and the learning of new ranking models with this factor. As a result of this project, the new ranking formula has been released, leading to improvements in Products Search business metrics such as orders volume and usefulness of search results.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses