Best similarity metric for collaborative filtering?

Posted by allclaws on Stack Overflow See other posts from Stack Overflow or by allclaws
Published on 2009-11-15T18:29:13Z Indexed on 2010/05/08 23:28 UTC
Read the original article Hit count: 337

Filed under:

collaborative-filtering

|

product-recommendation

I'm trying to decide on the best similarity metric for a product recommendation system using item-based collaborative filtering. This is a shopping basket scenario where ratings are binary valued - the user has either purchased an item or not - there is no explicit rating system (eg, 5-stars).

Step 1 is to compute item-to-item similarity, though I want to look at incorporating more features later on.

Is the Tanimoto coefficient the best way to go for binary values? Or are there other metrics that are appropriate here? Thanks.

© Stack Overflow or respective owner

Related posts about collaborative-filtering

collaborative filtering in rails

as seen on Stack Overflow - Search for 'Stack Overflow'
I'm looking for a solution for collaborative filtering in rails or even possible examples. So far I have only found acts_as_recommendable which looks useful but I noticed it hasn't had any updates in the last 2 years. Does anyone know of any other solutions and/or examples? >>> More
Collaborative Filtering Program: What to do for a Pearson Score When There Isn't Enough Data

as seen on Stack Overflow - Search for 'Stack Overflow'
I'm building a recommendation engine using collaborative filtering. For similarity scores, I use a Pearson correlation. This is great most of the time, but sometimes I have users that only share a 1 or 2 fields. For example: User 1{ a: 4 b: 2 } User 2{ a: 4 b: 3 } Since this is only 2 data points… >>> More
Collaborative filtering in MySQL ?

as seen on Stack Overflow - Search for 'Stack Overflow'
Hi I'm trying to develop a site that recommends items(fx. books) to users based on their preferences. So far, I've read O'Reilly's "Collective Intelligence" and numerous other online articles. They all, however, seem to deal with single instances of recommendation, for example if you like book A… >>> More
Converting python collaborative filtering code to use Map Reduce

as seen on Stack Overflow - Search for 'Stack Overflow'
Using Python, I'm computing cosine similarity across items. given event data that represents a purchase (user,item), I have a list of all items 'bought' by my users. Given this input data (user,item) X,1 X,2 Y,1 Y,2 Z,2 Z,3 I build a python dictionary {1: ['X','Y'], 2 : ['X','Y','Z'], 3 : ['Z']} From… >>> More
Best similarity metric for collaborative filtering?

as seen on Stack Overflow - Search for 'Stack Overflow'
I'm trying to decide on the best similarity metric for a product recommendation system using item-based collaborative filtering. This is a shopping basket scenario where ratings are binary valued - the user has either purchased an item or not - there is no explicit rating system (eg, 5-stars). Step… >>> More

Related posts about product-recommendation

Product Recommendation: Good job scheduler for windows servers?

as seen on Server Fault - Search for 'Server Fault'
Looking for a mostly-GUI tool that is low cost (less then $1k, but not required) and allows you to create scheduled tasks and jobs without writing vbscript, batch files, or powershell. Something simple that speaks SMB/CIFS, SMTP, LDAP, etc. for such things as "delete some files based on a list of… >>> More
Product recommendation for SIEM/log management

as seen on Server Fault - Search for 'Server Fault'
I am looking at purchasing a SIEM/log management solution. I've read quite a few reviews but was wondering if you all had any personal preference. 2 products that I am especially interested in is Splunk and NitroSecurity's ESM and ELM product. Thanks. >>> More
Best similarity metric for collaborative filtering?

as seen on Stack Overflow - Search for 'Stack Overflow'
I'm trying to decide on the best similarity metric for a product recommendation system using item-based collaborative filtering. This is a shopping basket scenario where ratings are binary valued - the user has either purchased an item or not - there is no explicit rating system (eg, 5-stars). Step… >>> More
Any good Open Source or Cheap ASP.NET Catalog Applications

as seen on Stack Overflow - Search for 'Stack Overflow'
We're looking for a cheap-to-free "off the shelf" ASP.NET catalogue application, that will meet the following requirements: Support two kinds of listings: Suppliers of Services Suppliers of Products, and their Products Suppliers can be categorised by: Area of specialisation - including sub-categories Location Other… >>> More
Amazon like Ecommerce site and Recommendation system

as seen on Stack Overflow - Search for 'Stack Overflow'
Hello, I am planning to implement a basic recommendation system that uses Facebook Connect or similar social networking site API's to connect a users profile, based on tags do an analyze and by using the results, generate item recommendations on my e-commerce site(works similar to Amazon). I do… >>> More