Liang Wang

Principal Research Scientist

Research areas: Data Mining, Machine Learning and Fraud Analytics

Liang Wang, Visa Principal Researcher.

Biography

Dr. Liang Wang joined Visa Research as a Principal Research Scientist in February 2018. Liang received his Ph.D. in Computer Science from Faculté Polytechnique de Mons in 1993. He received a M.S. in Systems Engineering and B.S. in Electrical Engineering from Tianjin University in 1988 and 1985, respectively. Prior to joining Visa, Liang was a Senior Principal Data Scientist at Yahoo!, responsible for building traffic protection solutions for advertising platforms. Before working at Yahoo!, he was a Distinguished Scientist at eBay/PayPal, leading projects on risk detection on payment systems, and a Senior Scientist at FICO, focusing on bankcard fraud detection. His work on predictive models have been deployed in major financial institutions and saved multiple-millions of fraud losses for clients.

As a member of the Data Analytics team, his research interests are in data mining, machine learning and fraud analytics. Dr. Wang is the inventor of 20 patents and has published 30 papers in several international conferences and journals, including Institute of Electrical and Electronics Engineers (IEEE) Transactions on Fuzzy Systems (TFS) , International Journal of General Systems (IJGS), Conferences on Decision and Control (CDC) IEEE, and others.

Conferences

  • Wang, L., & Yen, J. (1999). Extracting fuzzy rules for system modeling using a hybrid of genetic algorithms and Kalman filter. Fuzzy Sets and Systems, 101(3), 353–362.
  • Wang, L., Yen, J. & Langari, R. (1999). Identifying fuzzy rule-based models using orthogonal transformation and backpropagation, Fuzzy Theory Systems, 1, 187-204.
  • Yen, J., & Wang, L. (1999). Simplifying fuzzy rule-based models using orthogonal transformation methods. IEEE Transactions on Systems, Man and Cybernetics, Part B (Cybernetics), 29(1), 13–24.
  • Yen, J., Wang, L., & Gillespie, W. (1998). Improving the Interpretability of TSK Fuzzy Models by Combining Global Learning and Local Learning. IEEE Transactions on Fuzzy Systems, 6, 362-372.
  • Yen, J., Wang, L., & Gillespie, W. (1998). A global-local learning algorithm for identifying Takagi-Sugeno-Kang fuzzy models. IEEE International Conference on Fuzzy Systems.
  • Yen, J., & Wang, L. (1998). Application of Statistical Information Criteria for Optimal Fuzzy Model Construction. IEEE Transactions on Fuzzy Systems, 6, 362-372.
  • Yen, J., & Wang, L. (1998). Granule-based Models. Handbook of Fuzzy Computation.
  • Langari, R., Wang, L., & Yen, J. (1997). Radial Basis Function Networks, Regression Weights, and the Expectation-Maximization Algorithm. IEEE Transactions on Systems, Man, and Cybernetics, 27, 613-623.
  • Yen, J., Wang, L., & Langari, R. (1997). Multiple fuzzy models for function approximation. North American Fuzzy Information Processing Society.
  • Wang, L., & Langari, R. (1996). Complex Systems Modeling via Fuzzy Logic. IEEE Transactions on Systems, Man, and Cybernetics, 26, 100-106.
  • Yen, J., Langari, R., & Wang, L. (1996). Principal Components, B-Splines, and Fuzzy System Reduction. International Journal of Uncertainty, Fuzziness, and Knowledge-Based Systems, 4, 561-572.
  • Yen, J., & Wang, L. (1996). An SVD-based Fuzzy Model Reduction Strategy. IEEE International Conference on Fuzzy Systems, 835-841.
  • Wang, L., Langari, R. (1996). Sugeno Models, Fuzzy Discretization, and the EM algorithm. Fuzzy Sets and Systems, 82, 279-288.
  • Langari, R., & Wang, L. (1996). Fuzzy Models, Modular Networks, and Hybrid Learning. Fuzzy Sets and Systems, 79, 141-150.
  • Wang, L., & Langari, R. (1996). A Variable Forgetting Factor RLS Algorithm with Application to Fuzzy Time-Varying Systems Identification. International Journal of Systems Science, 27, 205-214.
  • Wang, L., & Langari, R. (1996). Identification and Control of Nonlinear Dynamic Systems Using Fuzzy models. International Journal of Intelligent Control and Systems, 247-260.
  • Wang, L., & Langari, R. (1996). Identification of Time-Varying Fuzzy Systems. International Journal of General Systems, 25, 203-218.
  • Yen, J. & Wang, L. (1996). Constructing optimal fuzzy models using statistical information criteria. Journal of Intelligent and Fuzzy Systems, 7, 394-402.
  • Wang, L., & Langari, R. (1995). Building Sugeno-Type Models Using Fuzzy Discretization and Orthogonal Parameter Estimation Techniques. IEEE Transactions on Fuzzy Systems, 3, 454-458.
  • Wang, L., & Langari, R. (1995). A Decomposition Approach for Fuzzy Systems Identification. IEEE Conference on Decision and Control.
  • Wang, L., & Langari, R. (1995). Fuzzy Systems with Competitive Objectives. American Control Conference. 
  • Langari, R., & Wang, L. (1995). A Modified RBF Network with Application to System Identification. IEEE Conference on Control Applications.
  • Wang, L., & Libert, G. (1994). Combining Pattern Recognition Techniques with Akaike's Information Criteria for Identifying ARMA Models. IEEE Transactions on Signal Processing, 42, 1388-1396.
  • Wang, L., & Langari, R. (1993). Fuzzy Controller Design via Hyperstability Theory. IEEE International Conference on Fuzzy Systems, 178-182.
  • Wang, L., & Thury, G. (1993). Modeling Economic Time Series via Innovation State Space Approach. International Conference on Systems Science and Systems Engineering.
  • Libert, G., Wang, L., & Liu, B. (1993). An Innovation State Space Approach for Time Series Forecasting. Journal of Time Series Analysis, 14, 589-601.
  • Libert, G., Liu, B., & Wang, L. (1992). The Choice of a Forecasting Model. Journal of Systems Science and Systems Engineering, 1, 1-11.
  • Wang, L., & Libert, G. (1992). Combining Forecasts Using Recursive Weighting and Linear Programming. IEEE Conference on Decision and Control, 3705-3706.
  • Wang, L., & Libert, G., & Liu, B. (1992). An expert system for forecasting model selection. IEEE Conference on Control Applications.
  • Wang, L., Libert, G., & Manneback, P. (1992). Kalman Filtering Algorithm based on Singular Value Decomposition. IEEE Conference on Decision and Control, 1224-1229.

Patents

  • Zhang, W., Wang, L., Christensen, R., Zheng, Y., Gou, L., & Yang, H. (2019). Transaction Sequence Processing with Embedded Decision Feedback.  U.S. Patent No. 3467US01. U. S. Patent and Trademark Office.
  • Wang, L., Gelda, D., Christensen, R., Zheng, Y., Zhang, W., & Yang, H. (2019). Method and System for Assessing the Reputation of a Merchant, U.S. Patent No. 3873US01. U. S. Patent and Trademark Office.
  • Dong, X., Ebrahimi, J., Zhang, W., & Wang, L. (2019). Methods and Systems for Cross-Domain Restaurant Recommendations, U.S. Patent No. 16,689,932. U. S. Patent and Trademark Office.
  • Zheng, Y., Wang, Y., Zhang, W., Yeh, M., & Wang, L. (2019). Unsupervised Embedding Disentanglement using a GAN for Merchant Recommendations.  U.S. Patent No. 4321US01. U. S. Patent and Trademark Office.
  • Wang, L., Qiu, A., Peng, L., & Zhang, J. (2018). Method and System for Assessing the Riskiness of a Domain from a Bid Request. U.S. Patent No. 15,946,190. U. S. Patent and Trademark Office.
  • Wang, L., Dong, X., Christensen, R., Gou, L., Zhang, W. & Yang H. (2018), System, Method, and Computer Program Product for Incorporating Knowledge from More Complex Models in Simpler Models, US Patent No. 16,244,240. U. S. Patent and Trademark Office.
  • Wang, L., Pratt, M., Zhang, J., & Taneja, A. (2017). Enhanced Fraud Detection with Terminal Transaction-Sequence Processing. U.S. Patent No. 12,058,554. U. S. Patent and Trademark Office.
  • Wang, L., Pratt, M., Zhang, J., & Taneja, A. (2017). Enhanced Fraud Detection with Terminal Transaction-Sequence Processing. EP Patent No. 1,975,869. European Patent Office.
  • Wang, L., Xia, Z., Chen, D., Han, Y., & Wang, R. (2017). Identifying User’s Identity through Tracking Common Activity. U.S. Patent No. 14,854,726. U. S. Patent and Trademark Office.
  • Wang, L., Qiu, A., Han, C., Han, Y., & Wang, R. (2017). Adaptive Scoring of Service Requests. U.S. Patent No. 15,800,159. U. S. Patent and Trademark Office.
  • Wang, L., Qiu, A., Han, C., & Peng, L. (2017). Method and System for Detecting Abnormal Online User Activities. U.S. Patent No. 10,419,460. U. S. Patent and Trademark Office.
  • Wang, L., Qiu, A., Han, C., & Salonen, T. (2017). Method and System for Identifying Fraudulent Publisher Networks. U.S. Patent No. 15,782,599. U. S. Patent and Trademark Office.
  • Wang, L., Qiu, A., Han, C., & Salonen, T. (2017). Method and System for Identifying Fraudulent Publisher Networks. European Patent No. 3,471,045. European Patent Office.
  • Qiu, A., Wang, L., Han, C., & Morales, J. (2017). Method and System for Data Center Bot Traffic Protection. U.S. Patent No. 15,794,991. U. S. Patent and Trademark Office.
  • Qiu, A., Wang, L., & Peng, L. (2017). Method and System for detecting Fraudulent User-content Provider Pairs. U.S. Patent No. 15,857,943.  U. S. Patent and Trademark Office.
  • Wang, L., Qiu, A., & Pan, A. (2017). Method and System for Reducing Risk Values Discrepancies between Categories. U.S. Patent No. 15,846,500. U. S. Patent and Trademark Office.
  • Zoldi, S., Wang, L., Sun., L., & Steven, W. (2005). Mass Compromise/Point Compromise Analytic Detection and Compromised Card Portfolio Management System. U.S. Patent No. 7,761,379. U. S. Patent and Trademark Office.
  • Zoldi, S., Wang, L., Sun., L., & Steven, W. (2005). Mass Compromise/Point Compromise Analytic Detection and Compromised Card Portfolio Management System. U.S. Patent No. 7,945,515. U. S. Patent and Trademark Office.
  • Zoldi, S., Wang, L., Sun., L., & Steven, W. (2005). Mass Compromise/Point Compromise Analytic Detection and Compromised Card Portfolio Management System. European Patent No.1,904,965. European Patent Office.
  • Zoldi, S., Wang, L., Sun., L., & Steven, W. (2005). Mass Compromise/Point Compromise Analytic Detection and Compromised Card Portfolio Management System. WO Patent No. 200,700,270.2. World Intellectual Property Organization.