Shih-Fen Cheng: Research: Predictive Mobile Crowdsourcing

Home
CV
Research
Publications
Teaching
People
Events
Links

Mobile crowdsourcing allows workers to flexibly perform location-specific tasks and receive compensation. For this to work, workers must have GPS-equipped smartphones and other sensors (e.g., camera or microphone, depending on the task type). Notable examples that follow this paradigm include: package delivery (e.g., Amazon Flex), ride-hailing (e.g., Uber, Grab), marketing audit (e.g., Field Agent, Gigwalk), food delivery (e.g., DoorDash, Deliveroo), and grocery delivery (e.g., Instacart, Amazon Fresh).

Traditional approach for task allocation either relies on independent worker's choices or centralized allocations using proximity-driven criterion. Therefore, the major research question we would want to answer is: Can we make mobile crowdsourcing more efficient by utilizing insights into worker's movement patterns or behavioral preferences?

We pioneered a push-based approach for MCS, in which the MCS platform utilize learned worker trajectory patterns to maximize task completion while minimize worker detour [1, 2]. The prototype of our idea, Ta$ker, is field-tested on the SMU campus for 3+ years, with 1000+ participating students and 100,000 tasks completed [3]. Through extensive randomized experiment with both push-based and pull-based approaches, and various ideas in MCS applications, we have the following findings:
  1. The push-based approach completes 56% more tasks with 30% less worker detour, and workers tend to accept tasks more in advance [3].
  2. Among super agents (workers who devote the most amount of time), push-based super agents is 25% more efficient than the pull-based super agents [3].
  3. Density-based adaptive pricing can help to achieve more uniform task completion across locations and fairer user reward distribution [4].
  4. When allocating tasks in bundles, workers are more productive in time, earn more per minute, and incur lower detours [4].
  5. Protect worker's location privacy by the development of obfuscation strategies. With careful design, we can protect worker's privacy with only minor impact on the overall productivity [6].



Related Publication

  1. Cen Chen, Shih-Fen Cheng, Aldy Gunawan, Archan Misra, Koustuv Dasgupta, and Deepthi Chander. TRACCS: A framework for trajectory-aware coordinated urban crowd-sourcing, Second AAAI Conference on Human Computation and Crowdsourcing (HCOMP-14), pages 30-40, Pittsburgh, PA, USA, November 2014.
  2. Cen Chen, Shih-Fen Cheng, Hoong Chuin Lau, and Archan Misra. Towards city-scale mobile crowdsourcing: Task recommendations under trajectory uncertainties, Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-15), pages 1113-1119, Beunos Aires, Argentina, July 2015.
  3. Thivya Kandappu, Archan Misra, Shih-Fen Cheng, Nikita Jaiman, Randy Tandriansyah, Cen Chen, Hoong Chuin Lau, Deepthi Chander, and Koustuv Dasgupta. Campus-scale mobile crowd-tasking: Deployment and behavioral insights, Nineteenth ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW-16), to appear, San Francisco, CA, USA, February 2016.
    • Honorable mention for the best paper award (top 5% of all papers).
  4. Thivya Kandappu, Nikita Jaiman, Randy Tandriansyah, Archan Misra, Shih-Fen Cheng, Cen Chen, Hoong Chuin Lau, Deepthi Chander, and Koustuv Dasgupta. TASKer: Behavioral insights via campus-based experimental mobile crowd-sourcing, 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp-16), to appear, Heidelberg, Germany, September 2016.
  5. Thivya Kandappu, Archan Misra, Shih-Fen Cheng, and Hoong Chuin Lau. Privacy in context-aware mobile crowdsourcing systems, Fourth International Workshop on Crowd Assisted Sensing, Pervasive Systems and Communications (CASPer 2017), in conjunction with 15th IEEE International Conference on Pervasive Computing and Communications (PerCom 2017), Kona, Big Island, Hawaii, USA, March 2017.
  6. Thivya Kandappu, Archan Misra, Shih-Fen Cheng, Randy Tandriansyah, and Hoong Chuin Lau. Obfuscation at-source: Privacy in context-aware mobile crowd-sourcing. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2(1): 16, 2018.
    • This paper was presented at the UbiComp 2018.
  7. Shih-Fen Cheng, Cen Chen, Thivya Kandappu, Hoong Chuin Lau, Archan Misra, Nikita Jaiman, Randy Tandriansyah, and Desmond Koh. Scalable urban mobile crowdsourcing: Handling uncertainty in worker movement, ACM Transactions on Intelligent Systems and Technology, 9(3): 26, 2018.
  8. Chung-Kyun Han, Archan Misra, and Shih-Fen Cheng. Mobility-driven BLE transmit-power adaptation for participatory data muling, IEEE Twenty-Fourth International Conference on Parallel and Distributed Systems (ICPADS-18), pages 962--971, Singapore, December 2018.
  9. Thivya Kandappu, Abhinav Mehrotra, Archan Misra, Mirco Musolesi, Shih-Fen Cheng, and Lakmal Buddika Meegahapola. PokeME: Applying context-driven notifications to increase worker engagement in mobile crowd-sourcing, Fifth ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR-20), Vancouver, Canada (Virtual), March 2020.
  10. Chung-kyun Han and Shih-Fen Cheng. An exact single-agent task selection algorithm for the crowdsourced logistics, 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-2020), Yokohama, Japan (Virtual), July 2020.
  11. Chung-Kyun Han and Shih-Fen Cheng. A Lagrangian column generation approach for the probabilistic crowdsourced logistics planning, 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE-2021), Lyon, France (Virtual), August 2021.

Awards and Recognition

Media

Last Modified: