1).Perform a Scenario Design analysis as described below. Consider whether it makes sense for your selected recommender system to perform scenario design twice, once for the organization (e.g. Amazon.com) and once for the organization’s customers.
The recommender system I want to perform scenario design analysis on is: Yelp. The age range of people who utilize Yelp is: 18-34. It looks like Yelp mostly targets college graduates. It is noted that around 60% of Yelp users are college graduates. Yelp’s goals are to provide a platform that would contain reviews of local businesses (mostly restaurants) and their customers. Yelp wants to create a connection between the customers and businesses in order to enhance each other. The platform provides full capabilities in allowing customers to express their opinions and having the businesses take this input and try to improve their business model in better serving these customers. In my opinion, Yelp does a great job in bringing the consumer and business together. It does well in allowing users the anonymity in being able to post their reviews and provide feedback to the business. In turn, the goal of the business is to then take this feedback and improve themselves to provide a better service to the consumers. However, I think that Yelp should reach out to a larger variety of consumers. I think that their consumer base is limiting (18-34) year old and mostly college graduates. I think that Yelp should encourage older customers to use their services by facilitating their experience. One way of doing this is to “Automate the Ask”. This can be done by creating a chat bot which, as soon as they login, will ask them the business they want to rate. A questionnaire (with multiple choice questions) might also be put in front of them to make their experience easier. I think if these and a variety of features are built in (upon entrance of the website) it will encourage/allow all age group demographics to participate and provide their opinions about a particular business.
2).Attempt to reverse engineer what you can about the site, from the site interface and any available information that you can find on the Internet or elsewhere.
If I were to reverse engineer Yelp, I would make it work more interactively with users. As a user, upon entering the site I would like a chat bot to provide me with options on the restaurant/business I would want to rate. I think this would engage me more than just me having to search myself. Another tool I would add to Yelp is a variety of different questionnaires (possibly of different formats). These should be positioned in a place on a website which is easily seen/accessible to users. The user will then choose the questionnaire which best fits their liking and fill it out. In my mind this benefits both the users and Yelp themselves. It is beneficial to the users because it gives them the option to state their opinion in their liking and utilize the format which best works for them. This in turn makes conveying their opinion a more enjoyable process for the users. Yelp benefits by collecting valuable information about the customers which they can use to further enhance their website or even share with businesses (assuming everything is ethical).
3).Include specific recommendations about how to improve the site’s recommendation capabilities going forward.
I have a few recommendations about how I can improve Yelps recommendation capabilities going forward. Firstly, I would have a list of about 5 to 10 restaurants pop up (for them to rate) in front of a particular user upon them entering the site. These restaurants will be not more than a 10 mile radius from where the user resides. This list would be generated based on how frequently the restaurant was rated. The less times the restaurant was rated the more it will appear on a users screen (assuming it meets the 10 mile radius criteria). This would ensure that more restaurants would have customers opinions and a chance at improving their business. Rating distribution is not only important to restaurants who are unnoticed but also for Yelp because it helps strengthen the customer-business relationship.Another feature I would add is to recommend restaurants, which are outside the preferences of the users. For example, if the user specified they do not like certain characterisitics of a restaraunt they rated in the past, Yelp will match that characteristic with other restaraunts which were given that characteristic by other users. This way if a user wants to attend a restaraunt they can go to Yelp and see if it is in the list of the one’s which have the undesirable features and thus saving themselves time and avoid going to the restaraunt.