Difference between revisions of "Milestone 4 TuringMachine: Sustainable Reputation Mechanism; Insights from Finance Industry"

From crowdresearch
Jump to: navigation, search
(→‎Recommendation Systems)
(→‎Combineing Global and Local Effects)
Line 25: Line 25:
  
 
===Combineing Global and Local Effects ===
 
===Combineing Global and Local Effects ===
 +
* Combine baseline method with latent factor model
 
[[File:GaikwadRec.png|800px|center|Class]]
 
[[File:GaikwadRec.png|800px|center|Class]]
  
 
===Latent Factor Model for Workers to Task Recommendation  ===
 
===Latent Factor Model for Workers to Task Recommendation  ===
 
[[File:NgaikwadLF.png|800px|center|Class]]
 
[[File:NgaikwadLF.png|800px|center|Class]]

Revision as of 22:24, 25 March 2015

Influence and Related work

The Future of Work, Kittur etal 2013 and Genomes of Collective Intelligence Framework, Malone etal 2010 have shown that Reputation plays a big role in developing sustainable crowd sourcing communities. There is huge risk involve in the crowd sourcing work. Both requestors and workers are exposed to the risk related to payment or quality. We build our idea based on theories in structured finance and recommendation system.

Class

Requestor-Worker Ratings

  • Workers and requestors rate each other.
  • An automated tranche creation algorithm clusters workers into A to E category.
Class

Tranches Structure Penalties, Incentives, Default Risk

  • For the requestors in A tranche the minimum wage requirement is avg/below avg. However, for the requestors in D the minimum wage requirement is higher because he has a greater risk of default. Similar structure is designed for the worker. Please see figure 2.
  • Based on the ratings we can create the tranches of workers and requestors
  • This structure exposes the risk involved in the crowdsourcing platforms.
  • The workers can build the task portfolio using rating profiles and maximize the profit by diversifying the risk. For instance, a worker can select one task from tranch A, 3 from Avg, and rest from D.
Class


Automated Worker-Requestor Recommendations

Recommendation Systems

  • We combine Recommendation engine with Tranches and automatically match up requestors and workers.
Class

Combineing Global and Local Effects

  • Combine baseline method with latent factor model
Class

Latent Factor Model for Workers to Task Recommendation

Class
Retrieved from "http://crowdresearch.stanford.edu/w/index.php?title=Milestone_4_TuringMachine:_Sustainable_Reputation_Mechanism;_Insights_from_Finance_Industry&oldid=5124"