We are going to discuss a bad example of recommendation agent (RA) used by an Indonesian e-commerce/ online forum platform, Kaskus. You would immediately think that this platform performs badly these days, but you cannot be more wrong. Recently, Kaskus announced that the site has achieved 600,000,000 page views every month and 40,000,000 users registered to the site which certify Kaskus to be the biggest online forum in Indonesia (Lukman, 2014) and Indonesia’s #1 website in 2013 (Redwing, 2013).
Kaskus started as an online bulletin board forum for gamer communities (Wee, 2012). When the traffic picked up, the users saw the opportunity to sell their things in the forum and thus e-commerce threads were popping up everywhere. Seeing how many e-commerce threads were created, Kaskus established a sub-forum called Kaskus Jual Beli (KJB) or Kaskus Selling and Buying especially for e-commerce threads.
For a long period of time, KJB has no recommendation agent what so ever to assist the buyers when purchasing something. What it had was merely content filtering system which was very inefficient because KJB had too many thread posts. Recently, however, KJB started to implement rule based preference elicitation to its existing RA system. This new type of RA is arguably effective because there are many different types of item sold. For example, if we want to buy a puppy (Yes, real puppy!) then the condition rule such as “new” or “second” will not be valid anymore.
Also the sellers can put any information they want without being required to fill in complete information. In consequences, it is hard to find a trusted seller or a seller that actually has the item we want to buy. For example, out of the sellers that offer Siberian husky between the range price of Rp 4 Million- 6 Million there are sellers who offer to sell for Rp 15 or Rp 123,456. It is very common in KJB for sellers to discuss the price only when the buyers contact them personally and so having rule of price range in the recommendation agent will be inefficient. Moreover, there are often thread posts with items that have been sold and have not been taken down from the site and so we have to visit each post to see if the item is still available.
Having good recommendation agent increase decision quality and effort for the users and thus satisfaction and trust to the site (Xiao & Benbasat, 2007). However despite KJB neglecting its recommendation agent, the transactions over KJB does not seem to decline but in fact continue to increase. It may have been because KJB is the most complete provider of all kinds of goods and service in Indonesia (Mochtar, 2012). You can almost find anything in KJB, from voodoo service to luxurious cars or house. A large pool of items attracts more consumer which in return attracts more sellers and thus sustain KJB business model.
- Lukman, E. (2014, April 15). 18 Popular Online Shopping Sites in Indonesia (2014 Edition) . Retrieved from TechInAsia: http://www.techinasia.com/popular-online-shopping-platforms-in-indonesia/
- Mochtar, M. (2012, November 7). Payment System in Indonesia’s Largest Sell and Buy E-Commerce Platform. Retrieved from The Online Economy: Strategy and Entrepreneurship: http://www.onlineeconomy.org/tag/kaskus
- Redwing. (2013, July 20). The Top 40 Indonesian websites in Q2 2013. Retrieved from Redwing Asia: http://redwing-asia.com/analysis-posts/the-top-40-indonesian-websites-in-q2-2013/
- Wee, W. (2012, April 20). The Story and Future of Kaskus . Retrieved from TechInAsia: http://www.techinasia.com/story-future-kaskus/
- Xiao, B., & Benbasat, I. (2007). E-Commerce Product Recommendation Agents: Use, Characteristics, and Impact. MIS Quaterly, 31(1), 137-209.