Learn or Earn? - Intelligent Task Recommendation for Competitive Crowdsourced Software Development

Abstract

Background: Competitive crowdsourced development encourages online software developers to register for tasks offered on the crowdsourcing platform and implement them in a competitive mode. As a large number of tasks are uploaded daily, the scenery of competition is changing continuously. Without appropriate decision support, online developers often make task decisions in an ad hoc and intuitive manner. Aims: To provide dynamic decision support for crowd developers to select the task that fit best to their personal learning versus earning objectives, taking into account the actual competitiveness situation. Method: We propose a recommendation system called EX 2 ("EX-Square") that combines both explorative ("learn") and exploitative ("earn") search for tasks, based on a systematic analysis of workers preference patterns, technologies hotness, and the projection of winning chances. The implemented prototype allows dynamic recommendations that reflect task updates and competition dynamics at any given time. Results: Based on evaluation from 4007 tasks monitored over a period of 2 years, we show that EX 2 can explore and adjust task recommendations corresponding to context changes, and individual learning preferences of workers. A survey was also conducted with 14 actual crowd workers, showing that intelligent decision support from EX 2 is considered useful and valuable. Conclusions: With support from EX 2 , workers benefit from the tool from getting customized recommendations, and the platform provider gets a higher chance to better cover the breadth of technology needs in case recommendations are taken.

CrowdAssist: A multidimensional decision support system for crowd workers

“…We used Xgboost 49 implementation for gradient boosting and scikit‐learn 50 implementation for other ML algorithms. Karim et al 51 have captured the dynamics of task selection behavior of workers on Topcoder data. They also proposed the approach for task recommendation that fit best to worker's personal learning versus earning objectives.…”

A KSAO Based Solvers’ Competency Model in Crowdsourcing Contests

“…Relevant studies under this mode are sufficient whether it is recommended for solvers [3], seekers [4], even to recommend partners [5]. However, there is relatively less research under competitive crowdsourcing [6], in which a seeker releases a task on the crowdsourcing contest platform, and the solver, as an individual or an organization, submits the solutions before the deadline, the solver whose solution is chosen is the winner and wins the prize in the end.…”

Freelancers in the Software Development Process: A Systematic Mapping Study

“…Project Planning [25] Requirement Management [20] Programming/Coding [14,21,37] Software Testing [7,17] Software Integration [7] Debugging [40] Software Evolution [40] Generic development [8][9][10][11][12][13]15,16,18,19,[22][23][24][26][27][28][29][30][31][32][33][34][35][36]38,39,41,42] The activities mentioned in Table 5 are the only software engineering activities where freelancers were involved as reported by the literature studies. The formulation of the category labels and classification of the studies in these categories were made on the basis of the software engineering activity that the literature studies have focused on.…”