A model of user behavior that predicts the likelihood of conversion and ad clicks

Case study

Challenge

Build a user behavior model for a given user and product that predicts the likelihood that the user will click on that product.

Organization profile

RTB House is one of the first retargeting companies in the world that developed and implemented a proprietary technology based entirely on DL solutions for the purchase of RTB ads. In 2018, the company was ranked eighth among technology companies in the Financial Times 1000:

Europe’s Fastest-Growing Companies 2018, won the Silver Stevie® Award as the most innovative company of the year and received the AIconics Award in the Best Application of AI for Sales & Marketing category and Big Innovation Award granted by the Business Intelligence Group.

Solution

Our algorithm made it possible to accurately predict user actions, which is a key component of RTB House technology.

In other words, for a given user and product, we need to predict the likelihood that the user will click on that product. Our job is to test a variety of models including neural networks, gradient boosting, random forests, factorization machines and various types of regression. We used many techniques, such as KNN-related functions obtained with LSH (locality-sensitive hashing).

Our LSH regression is available as open source in the Practical Approximation Algorithms Library (PAAL)! The solution was created by verifying various hypotheses and testing many different ideas. The cooperation contributed to the rapid development of RTB House and the global success in the online advertising market.

Revenue increase of 14.2 percent with the same percentage of gross margin and reduction of required resources.

MIM Solutions developed a cutting-edge user behaviour model that after 3 days of integration increased turnover by 14.2% (keeping the same gross margin percentage and decreased the required amount of resources needed). Cooperation has contributed to exponential growth of RTB House company and global success in the on-line advertisement market!

We would like to express our satisfaction on the cooperation regarding the development of our web application. Piotr Wygocki and the development team did a very professional job. We are satisfied with the solution given to us and with the communication flow through the project. We would like to recommend Piotr Wygocki and his development team. We look forward to working with them in future projects.

The ML/AI production-grade projects require adopting very practical approach. Our cooperation with MIM Solution was a true pleasure; they are professional, highly skilled and thorough. Therefore I highly recommend collaborating with the team, both at conceptual stage as well as in delivery.

I am really impressed by the quality of services I receive from MIM Solutions. They are definitely professionals. They do not miss deadlines, cooperation with them is smooth and they are fully committed to what they do. They are world-class specialists in their field. Even the most difficult challenges in the field of algorithmics, data analysis and artificial intelligence are feasible for them.

If you want to learn more how MIM Solutions can help develop AI in your company, please contact us.

Name

E-mail

Phone number

Subject

Message

Zgoda

I consent to the processing of my personal data in accordance with the Personal Data Protection Act in connection with sending an inquiry via the above contact form. Providing data is voluntary, but necessary for processing and answering the inquiry. I have been informed that I have the right to access my data, the possibility of correcting it, and requesting the cessation of its processing. The data administrator is MIM Solutions, ul. Świeradowska 47, 02-662 Warsaw, KRS: 0000581404, NIP: PL5213710082.

Case study