Solving Team Making Problem for Crowdsourcing with Evolutionary Strategy

Wang, Han; Zhang, Ren; Li, Xiaochen; Jiang, He

doi:10.1109/dsa.2018.00021

Cited by 4 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address these challenges, existing research has explored various methods and techniques to bridge the information gap between demand and supply in crowdsourcingbased software development. Such research includes studies towards developing a better understanding of worker motivation and preferences in CSD [3] [4] [5] [6], studies focusing on predicting task failure [7] [8]; studies employing modeling and simulation techniques to optimize CSD task execution processes [9] [10] [11]; and studies for recommending the most suitable workers for tasks [12] and developing methods to create crowdsourced teams [13] [14]. The existing work lacks effective supports for analyzing the impact of task similarity and task arrival date on task failure.…”

Section: Introductionmentioning

confidence: 99%

An Evolutionary Algorithm for Task Scheduling in Crowdsourced Software Development

Saremi¹,

Yagnik²,

Togelius³

et al. 2021

Preprint

View full text Add to dashboard Cite

The complexity of software tasks and the uncertainty of crowd developer behaviors make it challenging to plan crowdsourced software development (CSD) projects. In a competitive crowdsourcing marketplace, competition for shared worker resources from multiple simultaneously open tasks adds another layer of uncertainty to potential outcomes of software crowdsourcing. These factors lead to the need for supporting CSD managers with automated scheduling to improve the visibility and predictability of crowdsourcing processes and outcomes. To that end, this paper proposes an evolutionary algorithm-based task scheduling method for crowdsourced software development. The proposed evolutionary scheduling method uses a multiobjective genetic algorithm to recommend optimal task start date. The method uses three fitness functions, based on project duration, task similarity, and task failure prediction, respectively. The task failure fitness function uses a neural network to predict the probability of task failure with respect to a specific task start date. The proposed method then recommends the best tasks' start dates for the project as a whole and each individual task so as to achieve the lowest project failure ratio. Experimental results on 4 projects demonstrate that the proposed method has the potential to reduce project duration by a factor of 33-78%.

show abstract

Section: Introductionmentioning

confidence: 99%

An Evolutionary Algorithm for Task Scheduling in Crowdsourced Software Development

Saremi¹,

Yagnik²,

Togelius³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…To address these challenges, existing methods have explored various methods and techniques to bridge the information gap between demand and supply in crowdsourcing-based software development. These includes: studies towards developing better understanding of worker motivation and preferences in CSD [5][6][4] [32], studies focusing on predicting task failure [9] [10]; studies employing modeling and simulation techniques to optimize CSD task execution processes [21][23] [29]; and studies for recommending the most suitable workers for tasks [31] and developing methods to create crowdsourced teams [30] [33]. However, there is a lack of study on the task execution flow in the field of software crowdsourcing.…”

Section: Introductionmentioning

confidence: 99%

Impact of Task Cycle Pattern on Project Success in Software Crowdsourcing

Saremi¹,

Saremi²,

Jena³

et al. 2021

Preprint

View full text Add to dashboard Cite

Crowdsourcing is becoming an accepted method of software development for different phases in the production lifecycle. Ideally, mass parallel production through Crowdsourcing could be an option for rapid acquisition in software engineering by leveraging infinite worker resource on the internet. It is important to understand the patterns and strategies of decomposing and uploading parallel tasks to maintain a stable worker supply as well as a satisfactory task completion rate. This research report is an empirical analysis of the available tasks' lifecycle patterns in crowdsourcing. Following the waterfall model in Crowdsourced Software Development (CSD), this research identified four patterns for the sequence of task arrival per project: 1) Prior Cycle, 2) Current Cycle, 3) Orbit Cycle, and 4) Fresh Cycle.

show abstract

Impact of Task Cycle Pattern on Project Success in Software Crowdsourcing

Saremi

Jena

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Solving Team Making Problem for Crowdsourcing with Evolutionary Strategy

Cited by 4 publications

References 26 publications

An Evolutionary Algorithm for Task Scheduling in Crowdsourced Software Development

An Evolutionary Algorithm for Task Scheduling in Crowdsourced Software Development

Impact of Task Cycle Pattern on Project Success in Software Crowdsourcing

Impact of Task Cycle Pattern on Project Success in Software Crowdsourcing

Contact Info

Product

Resources

About