Having earned a master’s degree in applied economics from Johns Hopkins University, Shengkun Wang decided to pursue a Ph.D. in computer science. He was attracted to Virginia Tech and the Sanghani Center by “strong faculty, a great location, and an excellent academic atmosphere.”

Wang’s research focus on building multimodal models for financial time series forecasting stems from his background in finance.

“For example,” he said. “I combine stock-related features with tweets to predict price movements, use earnings calls to assess volatility, and integrate satellite imagery with point of interest datasets to estimate regional housing prices.”

While working on his master’s degree he encountered firsthand the challenges of making accurate predictions in complex markets and realized that combining multiple data sources through advanced machine learning techniques could significantly enhance forecasting accuracy and provide actionable insights.

 “This practical perspective motivated me to pursue research that not only advances theoretical understanding, but also has tangible applications in the industry,” said Wang. 

Wang, who is advised by Chang-Tien Lu, said that what he likes best about being a student at the Sanghani Center is the opportunity to engage in flexible research directions and the many opportunities offered for collaboration.

Among his papers presented at conferences are:

·      “Stock Movement and Volatility Prediction from Tweets, Macroeconomic Factors and Historical Prices,” at the 2023 IEEE International Conference on Big Data;

·      “JarviX: A LLM No code Platform for Tabular Data Analysis and Optimization,” at the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP);

·      “ALERTA-Net: A Temporal Distance-Aware Recurrent Networks for Stock Movement and Volatility Prediction,” at the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM);

·      “Self-Correlation and Cross-Correlation Learning for Few-Shot Remote Sensing Image Semantic Segmentation,” at ACM SIGSPATIAL 2024; 

·      “AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility Prediction,” at the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL);

·       “FHIRViz: Multi-Agent Platform for FHIR Visualization to Advance Healthcare Analytics,” at the 15thACM Conference on Bioinformatics, Computational Biology, and Health Informatics (BCB 2024); and

·      “DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos,” at the 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2024). 

Wang’s goal after graduation is to work in an industry position where he can conduct AI-related research and develop AI-related applications.