Importance of Context in Prediction Systems of Mobile Applications
Chetashri Bhadane1, Ketan Shah2, Parth Jhunjhunwala3, Ayush Kothari4
1Chetashri Bhadane*, Assistant Professor, Department of Computer Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India.
2Dr. Ketan Shah, Professor, SVKM’s MPTSME, Mumbai, India.
3Parth Jhunjhunwala, Department of Computer Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India.
4Ayush Kothari, Department of Computer Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India.
Manuscript received on February 28, 2020. | Revised Manuscript received on March 22, 2020. | Manuscript published on March 30, 2020. | PP: 5826-5831 | Volume-8 Issue-6, March 2020. | Retrieval Number: F9449038620/2020©BEIESP | DOI: 10.35940/ijrte.F9449.038620
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Many traditional systems give recommendations to the users based on their past history without considering the context of the situation the user is in currently. Such systems may be good at prediction based on the past but do not consider the rapidly changing environment and the prediction may not be the best for the user. Context personalized to the user is important because it explains the situation the user is in. The recommendations to the user should also change according to the various contexts present. Context often represents the hidden state information that the user is in currently. Many systems often take into consideration the location of the user because the situation of the user generally changes with the location. In this paper, we explain why context is important while predicting results for the users by reviewing a set of papers where different contexts such as weather, time, location, user preference, and activity have been taken into consideration. These papers have taken context such that the recommendations to users change dynamically according to their situation or location and these recommendations can be of various forms such as search results or targeted advertisement. Location based Services, Location based advertisement and several types of context have also been discussed in the paper. A general architecture of context-aware systems has also been proposed. Several real world companies also make use of this contextual information so that the user has a dynamic user experience where all the states which might affect his decision making are taken into consideration.
Keywords: Context-aware, Recommendation systems, Location-based context, Time-based context.
Scope of the Article: High Performance Computing.