Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Structural analysis of user choices for mobile app recommendation
Liu B., Wu Y., Gong N., Wu J., Xiong H., Ester M. ACM Transactions on Knowledge Discovery from Data11 (2):1-23,2016.Type:Article
Date Reviewed: Mar 14 2017

Mobile apps are rapidly evolving due to ongoing improvements in smartphone technology. However, the use of mobile devices introduces some obstacles for rookie users. How should novice users locate suitable apps from a hierarchy of apps to accomplish different tasks? How should rival mobile apps with comparable operational services be effectively recommended to users? In efforts to improve app recommendation based on the interests and proclivities of users, Liu and colleagues present a structural user choice model (SUCM) for ascertaining the well-organized classification and viable associations between apps.

In the SUCM, a user first decides on the type of apps to use prior to selecting the suitable app category/subcategory. The model requires the user to choose from the root of mobile apps, and then proceed through levels of categories and subcategories of apps until the user’s preferences are optimally satisfied. A probabilistic algorithm called the softmax function is used to examine the relationships among competing nodes of apps, in efforts to minimize the processing times for identifying the user’s preferences from numerous alternative app categories. This reliable algorithm is predicated on the theoretical foundations axioms of user preferences and choices. The authors compellingly present the log likelihood algorithms for understanding the dynamic parameters that are applied to effectively select among competing apps for the users.

The authors uniquely illustrate how SUCM works with a tree of alternative choices of apps from Google Play (music and audio, finance, sports, entertainment, games, and so on). In an effort to assess the effectiveness of the SUCM, experiments were performed with data derived from the marketplace--Google Play data--which contained several apps. Clearly, compared to the reputable currently available algorithms for ascertaining user-behavioral choices in the literature, the authors present more reliable results for distributing the apps to users based on their preferences. I encourage all statisticians and artificial intelligence advocates to read the exciting ideas in this paper.

Reviewer:  Amos Olagunju Review #: CR145119 (1706-0389)
Bookmark and Share
  Reviewer Selected
Featured Reviewer
 
 
Data Mining (H.2.8 ... )
 
 
Electronic Commerce (K.4.4 )
 
 
Information Search And Retrieval (H.3.3 )
 
Would you recommend this review?
yes
no
Other reviews under "Data Mining": Date
Feature selection and effective classifiers
Deogun J. (ed), Choubey S., Raghavan V. (ed), Sever H. (ed) Journal of the American Society for Information Science 49(5): 423-434, 1998. Type: Article
May 1 1999
Rule induction with extension matrices
Wu X. (ed) Journal of the American Society for Information Science 49(5): 435-454, 1998. Type: Article
Jul 1 1998
Predictive data mining
Weiss S., Indurkhya N., Morgan Kaufmann Publishers Inc., San Francisco, CA, 1998. Type: Book (9781558604032)
Feb 1 1999
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy