| Recommender systems using collaborative filtering are a popular technique for reducing information overload and finding products to purchase. However the economic model required to run a business around collaborative filtering is at odds with the end user's de sire for unvarnished recommendations. Traditional recommender systems are centralized and available only online which is at odds with the user's desire to have recommendations wherever they are. A personal recommender system will someday empower people with the technology needed to assert their freedom to share information of all kinds, and to take recommendations with them, wherever they go.; In this thesis we take three steps toward the long term vision of a personal recommender system. The PocketLens peer-to-peer collaborative filtering algorithm, the MultiLens recommendation framework, and MovieLens Unplugged.; We present the PocketLens collaborative filtering algorithm along with four peer-to-peer architectures for finding neighbors. We evaluate the architectures and algorithms in a series of experiments. These experiments show that PocketLens can run on portable and disconnected devices, give users control of their data, and produce recommendations that are as good as the best published algorithms to date.; We present the MultiLens framework. A new recommendation engine capable of combining multiple dimensions of preference and content information into a model used to make recommendations. We identify twelve application patterns used by recommender applications, and show how the MultiLens framework can be used to implement these patterns. We experimentally evaluate the ability of MultiLens to combine a content dimension with a quality dimension to solve the first rater and sparsity problems in collaborative filtering.; We present MovieLens unplugged, which examines several important challenges that interface designers must overcome on mobile devices: Providing sufficient value to attract prospective wireless users, handling occasionally connected devices, privacy and security, and surmounting the physical limitations of the devices. We present our experience with the implementation of a wireless movie recommender system on a cell phone browser, an AvantGo channel, a wireless PDA, and a voice-only phone interface. These interfaces help MovieLens users select movies to rent, buy, or see while away from their computer. |
