Context-Aware Recommender Systems (2010 - Present)
Users' preferences may vary from contexts to contexts (e.g., time, location, companion, occasions, weather, mood, budget, etc.) For example, a user may prefer action movies if he is watching movies by himself, while he may select romantic movies if he is going to watch movies with his partner. A user may choose a fast-food restaurant for a quick lunch by himself, but he may prefer a formal restaurant for a business dinner. Context-Aware Recommender Systems (CARS) can produce item recommendations to a user in specific contexts by adapting user preferences to different context situations. We build different recommendation models to capture users' preferences in contexts and deliver more effective context-aware recommendations. The open-source libraries, CARSKit and DeepCARSKit, are the key outputs in this project.

Multi-Criteria Decision Making (2017 - Present)

  • Multi-Criteria Decision Making (MCDM) refers to the process of determining the best feasible solution according to established criteria and problems that are common occurrences in everyday life. It is a sub-discipline of operations research that explicitly evaluates multiple conflicting criteria in decision making (both in daily life and in settings such as business, government and medicine). Multi-criteria recommender systems is one of the applications based on MCDM, while you may observe these applications in real-world, such as Yahoo! Movie, Tripadvisor.com, OpenTable.com, etc.

  • Sponsors


Deep Recommender Systems (2022 - Present)

  • Recommender systems have been widely applied to assist user decision making by delivering a list of personalized item recommendations. It is one of the most popular AI and machine learning applications, especial on the Internet, such as movie recommendations at Netflix and Youtube, playlist recommendations at Apple Music, product recommendations at Amazon.com, and so forth. In recent years, neural network based recommendation algorithms have been proposed and built to enhance the quality of recommendations. Dr. Yong Zheng and his research team received generous cloud computing credits from cloud service providers, so that they can utilize the computing-optimized machines and GPU resources to accerlate the computing in the process of developing and evaluating the deep recommender systems.

    Dr. Zheng and his team have received following supports:


    Products or outcomes by the supports:
    • DeepCARSKit: an open-source and deep learning based context-aware recommendation library

  • Sponsors


FinTech at Morningstar, Inc. (2022 - Present)

  • Financial technology (Fintech) is used to describe new tech that seeks to improve and automate the delivery and use of financial services. ​​​At its core, fintech is utilized to help companies, business owners, and consumers better manage their financial operations, processes, and lives by utilizing specialized software and algorithms that are used on computers and, increasingly, smartphones. Morningstar, Inc. is an American financial services firm headquartered in Chicago, Illinois. It provides an array of investment research and investment management services. With operations in 29 countries, Morningstar's research and recommendations are considered by financial journalists as influential in the asset management industry, and a positive or negative recommendation from Morningstar analysts can drive money into or away from any given fund. Through its asset management division, the firm currently manages over $244 billion as of March 31, 2021.

    Morningstar, Inc. collaborates with Dr. Zheng and his team on the following projects:

  • Sponsors


NSF Grant Proposal

  • Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review, Status: under review

  • Sponsors


Predictive Staffing Model (2020)

  • Digby's Detective & Security Agency (Digby) in Chicago is a firm that offers top-notch security and investigation services. Digby's firm assists the Chicago Transit Authority (CTA) on monitoring and reporting incidents on CTA bus, metro stations and rail yards. The project aims to utilize various data mining and machine learning techniques and build effective predictive staffing models which can predict or forecast the probability of transportation incidents at specific time and locations, so that Digby's firm can well-assign their staffs to the right place at the right time. This collaboration eventually brings multiple student internships to the ITM and CS departments at Illinois Institute of Technology, since 2020.

  • Sponsors


Student Travel Supports (2018 - Present)

  • As one of the professional services, Dr. Yong Zheng served as student support chairs regularly for academic conferences related to user modeling and human-centric AI. Dr. Yong Zheng seeks funding and sponsors to support student travels or attendances to these academic conferences. This activity supports the mission of NSF and other granting agencies to train more advanced professionals in Science, Technology, Engineering, and Mathematics (STEM). Attending conferences is difficult and expensive for students. Funding travel for graduate students has a broader impact. The funding provided by these funding agencies will have a significant impact to the careers of the future generation of researchers in the field of user modeling, human-centric AI, and other related fields by allowing them to attend and present their work at these premier conferences of the field. This will lead to the next generation of researchers in these research fields, striving to develop futuristic user-centered computing that can improve productivity, performance, and satisfaction of society at large.

    The list of supported conferences include but not limited to:

    • ACM Conference on User Modeling, Adaptation and Personalization (2018, 2019, 2020, 2021, 2022, 2023)
    • ACM Conference on Intelligent User Interfaces (2021, 2023)
    • ACM Conference on Hypertext and Social Media (2022)

    The list of funding agencies include but not limited to:
    • US National Science Foundation
    • ACM Special Interest Group on Computer–Human Interaction (SIGCHI)
    • ACM Special Interest Group on Hypertext and the Web (SIGWEB)
    • ACM Special Interest Group in Artificial Intelligence (SIGAI)
    • Springer Publisher
    • Microsoft, Inc.
    • User Modeling, Inc.

  • Sponsors