Predictive Mobile Crowdsourcing

Getting things done by leveraging the power of crowd.

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 (Chen et al., 2014; Chen et al., 2015; Cheng et al., 2018). 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 (Kandappu et al., 2016). Through extensive randomized experiment with both push-based and pull-based approaches, and various ideas in MCS applications, we have made the following contributions:

  1. The push-based approach completes 56% more tasks with 30% less worker detour, and workers tend to accept tasks more in advance (Kandappu et al., 2016).

  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 (Kandappu et al., 2016).

  3. Density-based adaptive pricing can help to achieve more uniform task completion across locations and fairer user reward distribution (Kandappu et al., 2016).

  4. When allocating tasks in bundles, workers are more productive in time, earn more per minute, and incur lower detours (Kandappu et al., 2016).

  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 (Kandappu et al., 2017; Kandappu et al., 2018).

In recent years, we also explored the uses of MCS paradigm in other application domains. For example, we have explored the use of mobile phones in transmitting data colletced from the Bluetooth Low Energy (BLE) sensors (Han et al., 2018). We also experimented with the idea of using MCS for serving last-mile delivery demands. In this line of research, we first propose a single-agent deterministic model (Han & Cheng, 2021), after which we extend the model to handle path stochasticity (Han & Cheng, 2021). From the platform operator’s perspective, we studied how to optimize the cost to serve last-mile deliveries by dynamically presenting tasks to crowd-source workers (Arslan et al., 2025).

References

2025

  1. Choice-based Crowdshipping for Next-day Delivery Services: A Dynamic Task Display Problem
    Alp Arslan, Firat Kilci, Shih-Fen Cheng, and 1 more author
    European Journal of Operational Research, Aug 2025

2021

  1. IJCAI-20
    An exact single-agent task selection algorithm for the crowdsourced logistics
    Chung-Kyun Han, and Shih-Fen Cheng
    In Twenty-Ninth International Joint Conference on Artificial Intelligence, Jan 2021
  2. CASE-21
    A Lagrangian column generation approach for the probabilistic crowdsourced logistics planning
    Chung-Kyun Han, and Shih-Fen Cheng
    In Seventeenth IEEE International Conference on Automation Science and Engineering, Aug 2021

2018

  1. Scalable urban mobile crowdsourcing: Handling uncertainty in worker movement
    Shih-Fen Cheng, Cen Chen, Thivya Kandappu, and 5 more authors
    ACM Transactions on Intelligent Systems and Technology, Aug 2018
  2. Obfuscation at-source: Privacy in context-aware mobile crowd-sourcing
    Thivya Kandappu, Archan Misra, Shih-Fen Cheng, and 2 more authors
    Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Aug 2018
  3. ICPADS-18
    Mobility-driven BLE transmit-power adaptation for participatory data muling
    Chung-Kyun Han, Archan Misra, and Shih-Fen Cheng
    In IEEE Twenty-Fourth International Conference on Parallel and Distributed Systems, Dec 2018

2017

  1. CASPer-17
    Privacy in context-aware mobile crowdsourcing systems
    Thivya Kandappu, Archan Misra, Shih-Fen Cheng, and 1 more author
    In Fourth International Workshop on Crowd Assisted Sensing, Pervasive Systems and Communications at Fifteenth IEEE International Conference on Pervasive Computing and Communications, Mar 2017

2016

  1. CSCW-16
    Campus-scale mobile crowd-tasking: Deployment and behavioral insights
    Thivya Kandappu, Archan Misra, Shih-Fen Cheng, and 6 more authors
    In Nineteenth ACM Conference on Computer-Supported Cooperative Work and Social Computing, Feb 2016
  2. UbiComp-16
    TASKer: Behavioral insights via campus-based experimental mobile crowd-sourcing
    Thivya Kandappu, Nikita Jaiman, Randy Tandriansyah, and 6 more authors
    In 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Sep 2016

2015

  1. IJCAI-15
    Towards city-scale mobile crowdsourcing: Task recommendations under trajectory uncertainties
    Cen Chen, Shih-Fen Cheng, Hoong Chuin Lau, and 1 more author
    In Twenty-Fourth International Joint Conference on Artificial Intelligence, Aug 2015

2014

  1. HCOMP-14
    TRACCS: A framework for trajectory-aware coordinated urban crowd-sourcing
    Cen Chen, Shih-Fen Cheng, Aldy Gunawan, and 3 more authors
    In Second AAAI Conference on Human Computation and Crowdsourcing, Nov 2014