Nilesh Patil

Head of AI at DreamStreet. Previously Head of Applied Research, Dream11.

Publications

You can also find my articles on my Google Scholar profile.

Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts

Published in Association for Computational Linguistics (ACL), 2026

Fine-tuning LLMs with structural guidance for robust entity resolution in linguistically diverse name-matching tasks.

Recommended citation: Chourasia, A., Kapoor, S., & Patil, N. (2026). Structure-Guided Entity Resolution: Fine-Tuning LLMs for Robust Name Matching in Complex Linguistic Contexts. Association for Computational Linguistics (ACL), Industry Track.
Download Paper

Optimizing Fantasy Sports Team Selection with Deep Reinforcement Learning

Published in CODS-COMAD '24, Association for Computing Machinery, 2024

Deep RL formulation of fantasy team selection under budget and lineup constraints, outperforming greedy and integer-programming baselines on historical lineups.

Recommended citation: Patil, N. et al. (2024). Optimizing Fantasy Sports Team Selection with Deep Reinforcement Learning. Proceedings of CODS-COMAD '24, ACM, 284–291.
Download Paper

Early Churn Prediction from Large Scale User-Product Interaction Time Series

Published in International Conference on Machine Learning and Applications (ICMLA), IEEE, 2023

Deep-learning approach to predicting user churn from interaction time series at 250M+ user scale, identifying churn risk far earlier than session-aggregate baselines.

Recommended citation: Patil, N. et al. (2023). Early Churn Prediction from Large Scale User-Product Interaction Time Series. 2023 International Conference on Machine Learning and Applications (ICMLA). IEEE.
Download Paper

Automated Ultrasound Doppler Angle Estimation Using Deep Learning

Published in 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2019

CNN-based pipeline that estimates the Doppler insonation angle from ultrasound B-mode images, removing a manual measurement step from clinical velocity workflows.

Recommended citation: Patil, N. et al. (2019). Automated Ultrasound Doppler Angle Estimation Using Deep Learning. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 28–31. IEEE.
Download Paper