Revenue Forecast for Growth Companies Using Scarce Time-Series Data

Investment professionals rely on extrapolating company revenue into the future to approximate the valuation of the companies in a high-growth stage. However, the financial data on growth companies is typically proprietary, costly and scarce, ruling out the wide adoption of data-driven approaches. As a result, we propose and productionize an efficient algorithm to perform long-term revenue extrapolation (with confidence estimation) using scarce data.

• We propose an efficient algorithm that can extrapolate revenue of growth companies (with confidence estimate) using scarce data.
• The revenue prediction indicates the valuation of the company, making the investment decisions informed.
• We will also briefly talk about how we productionize this algorithm on our investment platform.

————————————————————————————————————————————————————

Lele Cao – Staff Data Scientist & Motherbrain DS/ML Lead | EQT Partners

Lele Cao is a Senior Data Scientist at EQT Motherbrain. He has a Ph.D. (artificial intelligence) from the Department of Computer Science and Technology at Tsinghua University, an M.Sc. (interactive systems engineering) from Royal Institute of Technology, and a B.Eng. (software engineering) from Southeast University. He has published over 20 academic papers in the fields of machine learning and robotics, including 6 in AAAI, CVPR, IJCAI, EMNLP, ECML, RecSys. Lele has over 12 years of industrial experience from EQT, Activision Blizzard (King), Alibaba, Elisa, and Ericsson. He has 3 patents and supervised more than 8 master theses.

Vilhelm von Ehrenheim – Principal Engineer & Motherbrain Lead | EQT Partners

Vilhelm has over the last 5 years been building out the Motherbrain platform at EQT, leveraging Machine learning and data to make EQT an ever smarter investor. During this time the team has grown from 3 to 30 ppl and Motherbrain has become the central platform for tracking deal flow across EQT business lines. Before EQT Vilhelm was building production machine learning
systems at Klarna enabling real time decisions for credit and fraud risk.