Investigate DL/RL methods for processing overlength, noisy and obscure financial-related text, e.g. financial news, reports, posts, etc., particularly on summarization and sentiment analysis.
Investigate pattern discovery, clustering, and representation learning methods for temporal, heterogenous and large-scale financial behavior data, especially for anomaly detection applications.
Investigate machine learning methods for improving CTR/CVR for online advertisement recommendations, with special focus on cold-start prediction and model calibrations.
Created with Mobirise theme