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:
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).
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).
Density-based adaptive pricing can help to achieve more uniform task completion across locations and fairer user reward distribution (Kandappu et al., 2016).
When allocating tasks in bundles, workers are more productive in time, earn more per minute, and incur lower detours (Kandappu et al., 2016).
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).
This paper studies integrating the crowd workforce into next-day home delivery services. In this setting, both crowd drivers and contract drivers collaborate in making deliveries. Crowd drivers have limited capacity and can choose not to deliver if the presented tasks do not align with their preferences. The central question addressed is: How can the platform minimize the total task fulfilment cost, which includes payouts to crowd drivers and additional payouts to contract drivers for delivering the unselected tasks by customizing task displays to crowd drivers? To tackle this problem, we formulate it as a finite-horizon Stochastic Decision Problem, capturing crowd drivers’ utility-driven task preferences, with the option of not choosing a task based on the displayed options. An inherent challenge is approximating the non-constant marginal cost of serving orders not chosen by crowd drivers, which are then assigned to contract drivers. We address this by leveraging a common approximation technique, dividing the service region into zones. Furthermore, we devise a stochastic look-ahead strategy that tackles the curse of dimensionality issues arising in dynamic task display execution and a non-linear (problem specifically concave) boundary condition associated with the cost of hiring contract drivers. In experiments inspired by Singapore’s geography, we demonstrate that choice-based crowd shipping can reduce next-day delivery fulfilment costs by up to 16.9%.
The observed cost savings are closely tied to the task display policies and the task choice behaviors of drivers.
@article{EJOR_2025,title={Choice-based Crowdshipping for Next-day Delivery Services: A Dynamic Task Display Problem},volume={},pages={to appear},journal={European Journal of Operational Research},author={Arslan, Alp and Kilci, Firat and Cheng, Shih-Fen and Misra, Archan},year={2025},}
2021
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
The trend of moving online in the retail industry has created great pressure for the logistics industry to catch up both in terms of volume and response time. On one hand, volume is fluctuating at greater magnitude, making peaks higher; on the other hand, customers are also expecting shorter response time. As a result, logistics service providers are pressured to expand and keep up with the demands. Expanding fleet capacity, however, is not sustainable as capacity built for the peak seasons would be mostly vacant during ordinary days. One promising solution is to engage crowdsourced workers, who are not employed full-time but would be willing to help with the deliveries if their schedules permit. The challenge, however, is to choose appropriate sets of tasks that would not cause too much disruption from their intended routes, while satisfying each delivery task’s delivery time window requirement. In this paper, we propose a decision-support algorithm to select delivery tasks for a single crowdsourced worker that best fit his/her upcoming route both in terms of additional travel time and the time window requirements at all stops along his/her route, while at the same time satisfies tasks’ delivery time windows. Our major contributions are in the formulation of the problem and the design of an efficient exact algorithm based on the branch-and-cut approach. The major innovation we introduce is the efficient generation of promising valid inequalities via our separation heuristics. In all numerical instances we study, our approach manages to reach optimality yet with much fewer computational resource requirement than the plain integer linear programming formulation. The greedy heuristic, while efficient in time, only achieves around 40-60% of the optimum in all cases. To illustrate how our solver could help in advancing the sustainability objective, we also quantify the reduction in the carbon footprint.
@inproceedings{han_ijcai_2020,title={An exact single-agent task selection algorithm for the crowdsourced logistics},booktitle={Twenty-Ninth International Joint Conference on Artificial Intelligence},address={Yokohama, Japan (Virtual)},author={Han, Chung-Kyun and Cheng, Shih-Fen},year={2021},month=jan,}
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
In recent years we have increasingly seen the movement for the retail industry to move their operations online. Along the process, it has created brand new patterns for the fulfillment service, and the logistics service providers serving these retailers have no choice but to adapt. The most challenging issues faced by all logistics service providers are the highly fluctuating demands and the shortening response times. All these challenges imply that maintaining a fixed fleet will either be too costly or insufficient. One potential solution is to tap into the crowdsourced workforce. However, existing industry practices of relying on human planners or worker’s self-planning have been shown to be inefficient and laborious. In this paper, we introduce a centralized planning model for the crowdsourced logistics delivery paradigm, considering individual worker’s spatio-temporal preferences. Considering worker’s spatio-temporal preferences is important for the planner as it could significantly improve crowdsourced worker’s productivity. Our major contributions are in the formulation of the problem as a mixed-integer program and the proposal of an efficient algorithm that is based on the column generation and the Lagrangian relaxation frameworks. Such a hybrid approach allows us to overcome the difficulty encountered separately by the classical column generation and Lagrangian relaxation approaches. By using a series of real-world-inspired numerical instances, we have demonstrated the effectiveness of our approach against classical column generation and Lagrangian relaxation approaches, and a decentralized, agent-centric greedy approach. Our proposed hybrid approach is scalable to large problem instances, with reasonable solution quality, and achieves better allocation fairness.
@inproceedings{han_case_2021,title={A Lagrangian column generation approach for the probabilistic crowdsourced logistics planning},booktitle={Seventeenth IEEE International Conference on Automation Science and Engineering},address={Lyon, France (Virtual)},author={Han, Chung-Kyun and Cheng, Shih-Fen},year={2021},month=aug,}
In this article, we investigate effective ways of utilizing crowdworkers in providing various urban services. The task recommendation platform that we design can match tasks to crowdworkers based on workers’ historical trajectories and time budget limits, thus making recommendations personal and efficient. One major challenge we manage to address is the handling of crowdworker’s trajectory uncertainties. In this article, we explicitly allow multiple routine routes to be probabilistically associated with each worker. We formulate this problem as an integer linear program whose goal is to maximize the expected total utility achieved by all workers. We further exploit the separable structures of the formulation and apply the Lagrangian relaxation technique to scale up computation. Numerical experiments have been performed over the instances generated using the realistic public transit dataset in Singapore. The results show that we can find significantly better solutions than the deterministic formulation, and in most cases we can find solutions that are very close to the theoretical performance limit. To demonstrate the practicality of our approach, we deployed our recommendation engine to a campus-scale field trial, and we demonstrate that workers receiving our recommendations incur fewer detours and complete more tasks, and are more efficient against workers relying on their own planning (25% more for top workers who receive recommendations). This is achieved despite having highly uncertain worker trajectories. We also demonstrate how to further improve the robustness of the system by using a simple multi-coverage mechanism.
@article{cheng_tist_2018,author={Cheng, Shih-Fen and Chen, Cen and Kandappu, Thivya and Lau, Hoong Chuin and Misra, Archan and Jaiman, Nikita and Tandriansyah, Randy and Koh, Desmond},title={Scalable urban mobile crowdsourcing: Handling uncertainty in worker movement},journal={ACM Transactions on Intelligent Systems and Technology},volume={9(3):26},pages={1--24},year={2018},}
By effectively reaching out to and engaging larger population of mobile users, mobile crowd-sourcing has become a strategy to perform large amount of urban tasks. The recent empirical studies have shown that compared to the pull-based approach, which expects the users to browse through the list of tasks to perform, the push-based approach that actively recommends tasks can greatly improve the overall system performance. As the efficiency of the push-based approach is achieved by incorporating worker’s mobility traces, privacy is naturally a concern. In this paper, we propose a novel, 2-stage and user-controlled obfuscation technique that provides a trade off-amenable framework that caters to multi-attribute privacy measures (considering the per-user sensitivity and global uniqueness of locations). We demonstrate the effectiveness of our approach by testing it using the real-world data collected from the well-established TA$Ker platform. More specifically, we show that one can increase its location entropy by 23% with only modest changes to the real trajectories while imposing an additional 24% (< 1 min) of detour overhead on average. Finally, we present insights derived by carefully inspecting various parameters that control the whole obfuscation process.
@article{kandappu_imwut_2018,author={Kandappu, Thivya and Misra, Archan and Cheng, Shih-Fen and Tandriansyah, Randy and Lau, Hoong Chuin},title={Obfuscation at-source: Privacy in context-aware mobile crowd-sourcing},journal={Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},volume={2(1):16},pages={1--24},year={2018},}
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
This paper analyzes a human-centric framework, called SmartABLE, for easy retrieval of the sensor values from pervasively deployed smart objects in a campus-like environment. In this framework, smartphones carried by campus occupants act as data mules, opportunistically retrieving data from nearby BLE (Bluetooth Low Energy) equipped smart object sensors and relaying them to a backend repository. We focus specifically on dynamically varying the transmission power of the deployed BLE beacons, so as to extend their operational lifetime without sacrificing the frequency of sensor data retrieval. We propose a memetic algorithm-based power adaptation strategy that can handle deployments of thousands of beacons and tackles two distinct objectives: (1) maximizing BLE beacon lifetime, and (2) reducing the BLE scanning energy of the mules. Using real-world movement traces on the Singapore Management University campus, we show that the benefit of such mule movement-aware power adaptation: it provides reliably frequent retrieval of BLE sensor data, while achieving a significant (5-fold) increase in the sensor lifetime, compared to a traditional fixed-power approach.
@inproceedings{han_icpads_2018,title={Mobility-driven BLE transmit-power adaptation for participatory data muling},booktitle={IEEE Twenty-Fourth International Conference on Parallel and Distributed Systems},address={Singapore},author={Han, Chung-Kyun and Misra, Archan and Cheng, Shih-Fen},year={2018},month=dec,}
2017
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
Mobile crowd-sourcing can become as a strategy to perform time-sensitive urban tasks (such as municipal monitoring and last mile logistics) by effectively coordinating smartphone users. The success of the mobile crowd-sourcing platform depends mainly on its effectiveness in engaging crowd-workers, and recent studies have shown that compared to the pull-based approach, which relies on crowd-workers to browse and commit to tasks they would want to perform, the push-based approach can take into consideration of worker’s daily routine, and generate highly effective recommendations. As a result, workers waste less time on detours, plan more in advance, and require much less planning effort. However, the push-based systems are not without drawbacks. The major concern is the potential privacy invasion that could result from the disclosure of individual’s mobility traces to the crowd-sourcing platform. In this paper, we first demonstrate specific threats of continuous sharing of users locations in such push-based crowd-sourcing platforms. We then propose a simple yet effective location perturbation technique that obfuscates certain user locations to achieve privacy guarantees while not affecting the quality of the recommendations the system generates.We use the mobility traces data we obtained from our urban campus to show the trade-offs between privacy guarantees and the quality of the recommendations associated with the proposed solution. We show that obfuscating even 75% of the individual trajectories will affect the user to make another extra 1.8 minutes of detour while gaining 62.5% more uncertainty of his location traces.
@inproceedings{kandappu_casper_2017,author={Kandappu, Thivya and Misra, Archan and Cheng, Shih-Fen and Lau, Hoong Chuin},title={Privacy in context-aware mobile crowdsourcing systems},booktitle={Fourth International Workshop on Crowd Assisted Sensing, Pervasive Systems and Communications at Fifteenth IEEE International Conference on Pervasive Computing and Communications},address={Hawaii, USA},year={2017},month=mar,}
2016
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
Honorable mention for the Best Paper Award (top 5% of all papers).
Mobile crowd-tasking markets are growing at an unprecedented rate with increasing number of smartphone users. Such platforms differ from their online counterparts in that they demand physical mobility and can benefit from smartphone processors and sensors for verification purposes. Despite the importance of such mobile crowd-tasking markets, little is known about the labor supply dynamics and mobility patterns of the users. In this paper we design, develop and experiment with a realwporld mobile crowd-tasking platform, called TAKer. Our contributions are two-fold: (a) We develop TAKer, a system that allows us to empirically study the worker responses to push vs. pull strategies for task recommendation and selection. (b) We evaluate our system via experimentation with 80 real users on our campus, over a 4 week period with a corpus of over 1000 tasks. We then provide an in-depth analysis of labor supply, worker behavior & task selection preferences (including the phenomenon of super agents who complete large portions of the tasks) and the efficacy of pushbased approaches that recommend tasks based on predicted movement patterns of individual workers.
@inproceedings{kandappu_cscw_2016,author={Kandappu, Thivya and Misra, Archan and Cheng, Shih-Fen and Jaiman, Nikita and Tandriansyah, Randy and Chen, Cen and Lau, Hoong Chuin and Chander, Deepthi and Dasgupta, Koustuv},title={Campus-scale mobile crowd-tasking: Deployment and behavioral insights},booktitle={Nineteenth ACM Conference on Computer-Supported Cooperative Work and Social Computing},address={San Francisco, CA, USA},year={2016},month=feb,}
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
While mobile crowd-sourcing has become a game-changer for many urban operations, such as last mile logistics and municipal monitoring, we believe that the design of such crowdsourcing strategies must better accommodate the real-world behavioral preferences and characteristics of users. To provide a real-world testbed to study the impact of novel mobile crowd-sourcing strategies, we have designed, developed and experimented with a real-world mobile crowd-tasking platform on the SMU campus, called TAKer. We enhanced the TAKer platform to support several new features (e.g., task bundling, differential pricing and cheating analytics) and experimentally investigated these features via a two-month deployment of TA$Ker, involving 900 real users on the SMU campus who performed over 30,000 tasks. Our studies (i) show the benefits of bundling tasks as a combined package, (ii) reveal the effectiveness of differential pricing strategies and (iii) illustrate key aspects of cheating (false reporting) behavior observed among workers.
@inproceedings{kandappu_ubicomp_2016,author={Kandappu, Thivya and Jaiman, Nikita and Tandriansyah, Randy and Misra, Archan and Cheng, Shih-Fen and Chen, Cen and Lau, Hoong Chuin and Chander, Deepthi and Dasgupta, Koustuv},title={TASKer: Behavioral insights via campus-based experimental mobile crowd-sourcing},booktitle={2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing},address={Heidelberg, Germany},year={2016},month=sep,}
2015
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
In this work, we investigate the problem of large-scale mobile crowdsourcing, where workers are financially motivated to perform location-based tasks physically. Unlike current industry practice that relies on workers to manually pick tasks to perform, we automatically make task recommendation based on workers’ historical trajectories and desired time budgets. The challenge of predicting workers’ trajectories is that it is faced with uncertainties, as a worker does not take same routes every day. In this work, we depart from deterministic modeling and study the stochastic task recommendation problem where each worker is associated with several predicted routine routes with probabilities. We formulate this problem as a stochastic integer linear program whose goal is to maximize the expected total utility achieved by all workers. We further exploit the separable structures of the formulation and apply the Lagrangian relaxation technique to scale up computation. Experiments have been performed over the instances generated using the real Singapore transportation network. The results show that we can find significantly better solutions than the deterministic formulation.
@inproceedings{chen_ijcai_2015,author={Chen, Cen and Cheng, Shih-Fen and Lau, Hoong Chuin and Misra, Archan},title={Towards city-scale mobile crowdsourcing: Task recommendations under trajectory uncertainties},booktitle={Twenty-Fourth International Joint Conference on Artificial Intelligence},address={Beunos Aires, Argentina},year={2015},month=aug,}
2014
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
We investigate the problem of large-scale mobile crowd-tasking, where a large pool of citizen crowd-workers are used to perform a variety of location-specific urban logistics tasks. Current approaches to such mobile crowd-tasking are very decentralized: a crowd-tasking platform usually provides each worker a set of available tasks close to the worker’s current location; each worker then independently chooses which tasks she wants to accept and perform. In contrast, we propose TRACCS, a more coordinated task assignment approach, where the crowd-tasking platform assigns a sequence of tasks to each worker, taking into account their expected location trajectory over a wider time horizon, as opposed to just instantaneous location. We formulate such task assignment as an optimization problem, that seeks to maximize the total payoff from all assigned tasks, subject to a maximum bound on the detour (from the expected path) that a worker will experience to complete her assigned tasks. We develop credible computationally-efficient heuristics to address this optimization problem (whose exact solution requires solving a complex integer linear program), and show, via simulations with realistic topologies and commuting patterns, that a specific heuristic (called Greedy-ILS) increases the fraction of assigned tasks by more than 20%, and reduces the average detour overhead by more than 60%, compared to the current decentralized approach.
@inproceedings{chen_hcomp_2014,author={Chen, Cen and Cheng, Shih-Fen and Gunawan, Aldy and Misra, Archan and Dasgupta, Koustuv and Chander, Deepthi},title={TRACCS: A framework for trajectory-aware coordinated urban crowd-sourcing},booktitle={Second AAAI Conference on Human Computation and Crowdsourcing},address={Pittsburgh, PA, USA},year={2014},month=nov,}