Presentation: TweetA Real World Multifactor Recommender System & the Required Nextgen Integration Solution

Part one:
Creating recommendations using scalable technology, such as PIG, HIVE or Mahout, is one thing, but what does it take to develop an operating recommender system and what crucial customer behavioral factors are involved, what is the impact of the visual presentation of an item being recommended or the way customers move from one item to another?
Some questions related to using these customer behavior factors in a multifactor recommender system are:

• What should be the level of personalization?
• How does the real time behavior of the customer constrain the recommender system?
• How do we measure success when everything is constantly changing?

In this talk I will address the above mentioned questions and give insight into the multifactor recommender system of online retailer bol.com. Moreover, experiences will be shared with building this recommender system and the quality of its output.

Part two:
In online retail we apply the concept of Customer Centric Selling to ensure we shape the behavior of the website to optimally suit the needs of the visitor. Some details of this are presented in part one.
For a long time we have been able to preprocess earlier behavior for returning visitors to do this.
But what do you do if that visitor is anonymous? How do you respond to new behavior on the next page they view?

In this session we will show how we at bol.com have adapted the Lambda Architecture to meet our specific needs for this use case.