It is simple: Is your recommendation algorithm worth $1m? If it is, then, Overstock could be paying you. Or if your own is not good enough, you can still nominate someone for RecLab Prize. Nominations will be accepted until June 15, 2011. Read more about this opportunity for the tech wants.
Online product recommendations are among the shopping tools most widely used by consumers who need to easily find relevant and enticing products from the millions available online. Overstock.com has worked with RichRelevance since 2009 to present shoppers with dynamic recommendations that grow smarter over time and accurately reflect more than 60 different ways that people shop on the site (by price, by brand, by category). Now Overstock.com is partnering with RichRelevance to open up this real-world business challenge to the academic community, challenging academic researchers to advance the state of the art in personalized product recommendations by crafting an algorithm that delivers a 10% or greater lift over existing product recommendations on Overstock.com. If no team achieves a 10% lift, then smaller prizes will be awarded. A brief overview of the contest follows.
- Maximum Prize: $1,000,000
The winning team will receive a cash prize of $100,000 USD multiplied by the percentage that the entrant’s algorithm performed over RichRelevance’s algorithm—up to a maximum amount of $1,000,000. For example, if the winner produced 3.34% more revenue per session than RichRelevance’s algorithm, the winner will receive $330,000.
- Institution Prize: up to $250,000
Should the winning team be affiliated with an educational institution, up to 25% of the prize amount (funded separately from the Team Winner’s Prize) can be allocated to the educational institution(s).
- To register, visit http://overstockreclabprize.com/teams/register and complete the registration form
- To compete in the competition, your submission must be one of ten top Semi-Finalists chosen by a peer review committee appointed by Overstock.com and RichRelevance.
- If any of the Semi-Finalists produce 1% more revenue per session than existing algorithms, then the top three submissions (as measured by revenue per session) will be run on 10% of sessions each for an additional three weeks. The best performing of these algorithms, as judged by increase in revenue per session over the existing algorithms, will be eligible for a prize of up to $1,000,000.
Dec. 1, 2011