Next-Stop Recommender is an recommendation app with two bio-inspired time-series and sequential data mining algorithms (see http://nextstop.vipresearch.ca/ for relevant acadmic publications that VIP Research Group has done) implemented to predict and make Point of Interest (PoI) and PoI category recommendations for its users according to their anonymous time-series wandering history.
* * * * *
* * * * *
Next-Stop Recommender (https://nextstop.vipresearch.ca/) is version 3.0 of VIP Research Group's Next-Stop Recommendation research. The version 3.0 research has done through the following three stages.
Stage 1 (see https://youtu.be/JsX-FCJ35AI) includes the following major tasks/features (but not limited to):
1. anonymized device registration;
2. secure and anonymous synchronization for the visited Point of Interest (PoIs) and their categories;
3. a PoI's stay status detection; and,
4. local storage integrity checker and anonymous data synchronizer.
Stage 2 (see https://youtu.be/5S1HWDZKRSc) includes the following major tasks/features (but not limited to):
1. app's configuration settings;
2. offline map requester and synchronizer; and,
3. Next-Stop Recommender dashboard.
Stage 3 (see https://youtu.be/e5pFN3-xyzo) includes the following major tasks/features (but not limited to):
1. Route Recommendation algorithm;
2. Regular Expression based algorithm.
* * * * *
The Next-Stop Recommender is an app that implements the two time-series data mining algorithms VIP Research Group designed and published (see Relevant Publication section below or check them at https://nextstop.vipresearch.ca/).
The app (1) uses the algorithms to find the patterns of the anonymized and hashed point of interest (PoI) data caused by users' wandering behaviours and (2) matches and calculates the similarity among all patterns for recommending top N potential point of interest or PoI category that the users may be interesed for the users.
The app accesses user's location, behind the scene without user-facing interface. It matches the location's coordinates to an existing point of interest (PoI). If a location has a match to an existing PoI, then the app will check if its user spends enough time at the PoI according to the pre-defined PoI category based stay-time threshold. If the user spends enough time, then the app considers the user "visited" the PoI and creates a hashed record for the PoI and PoI category visit for the user.
* * * * *
- Ben Ripley, Dirksen Liu, Maiga Chang, and Kinshuk. (2013). Next Stop Recommender. In the Proceedings of 2013 International Joint Conference on Awareness Science and Technology and Ubi-Media Computing (iCAST-UMEDIA 2013), Aizuwakamatsu, Japan, November 2-4, 2013, 120-125.
- Siu Hung Keith Lo and Maiga Chang. (2012). An Innovative Way for Mining Clinical and Administrative Healthcare Data. Active Media Technology (AMT 2012), Macau, December 4-7, 2012, 528-533.
- Keith Lo. (2012). Health Care Data Mining from Clinical and Administrative Systems. Unpublished Master Essay, Athabasca University, Alberta, Canada.
- Dirksen Liu and Maiga Chang. (2011). Next-Stop Recommendation to Travelers according to Their Sequential Wandering Behaviours. Journal of Internet Technology, 12(1), 171-179.
- Dirksen Liu and Maiga Chang. (2009). Recommend Touring Routes to Travelers according to Their Sequential Wandering Behaviours. In the Proceedings of the 10th International Symposium on Pervasive Systems, Algorithms and Networks, (I-SPAN 2009), Kaohsiung, Taiwan, Dec. 14-16, 2009, 350-355.
- Dirksen Liu. (2009). Route Recommendation based on Behavior Analysis. Unpublished Master Essay, Athabasca University, Alberta, Canada.
* * * * *
For more details and frequently asked questions and their answers, please visit http://nextstop.vipresearch.ca/.