Now that we have covered basic techniques for recommender systems, choose one commercial recommender and describe how you think it works (content-based, collaborative filtering, etc). Does the technique deliver a good experience or are the recommendations off-target?
As per my previous work experience, our company was using item based collaborative recommender system which was actually working based on user’s previous buying history. It wasn’t working quite well for us as we were in handicraft sector and a lot of times they were buying the tools that they need to make those handicrafts and mostly it was need based. Later on, we started push strategy based on what customer’s preferences were and used hybrid approach which worked better for us. I think these recommender systems work good and the selection of the tools totally depend upon the industry and target market.
Read the article below and consider how to handle attacks on recommender systems. Can you think of a similar example where a collective effort to alter the workings of content recommendations have been successful? How would you design a system to prevent this kind of abuse?
I think that’s the case very much nowadays in most sectors. I can totally relate it with our company. As an e-commerce company we were selling our products to most of the platforms including Amazon and e-bay. Sometimes the customers were giving 1 star based on something insignificant and we had to beg them to remove the review. Amazon has strict policies on quality and if the product keeps getting negative reviews then it can be blocked to sell again. It can be stopped through numerous ways to identify the spam reviews and deletes them. ML techniques such as classifiers can be very useful in this situation to identify the biased reviews and remove them.