Efficient web navigation prediction using hybrid models based on multiple evidence combinations

Abstract

Modeling user(s) navigation sequences and predicting their preferences has been an interesting area of research. For Web Navigation Prediction (WNP) the Markov model(s) are predominantly used for analyzing and discovering user navigation patterns. One of the major issues with the Markov model is that it fails to predict for unclassified navigations. Presence of such navigations reduces the prediction power of the model. Deep machine learning models can be used to address unclassified navigations but their prediction ability deteriorates if training sessions are less in number. As Navigations have been modeled using N-Grams where the number of training sessions reduces at higher N-Grams. It might affect the performance of deep learning models. However, their prediction ability can be improvised by integrating it with the Markov model. This paper proposes three integrated models to minimize the unclassified navigations and to boost the overall prediction accuracy. Proposed hybrid models are formed by integrating All-Kth Markov Model with Deep Neural Network (DKM) and All-Kth Modified Markov Model with Shallow Neural Network and Deep Neural Network (SKMM and DKMM). The proposed models are evaluated on three standard datasets: CTI, BMS, and Wikispeedia. DKMM has obtained the best results in terms of improvement in prediction accuracy and reduction in unclassified navigations on higher N-grams. Prediction accuracy was improved up to 4.71, 6.2 and 7.67 in CTI, BMS and Wikispeedia dataset.

KEYWORDS:

• Web
• navigations
• prediction
• Markov
• perceptron
• Neural

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Honey Jindal

Honey Jindal is a Research Scholar in Computer Science and Engineering Department at Jaypee Institute of Information Technology, Noida, India. She received her M.Tech degree in Computer Science and Engineering from Jaypee Institute of Information Technology, Noida, India in July 2014, a B.Tech degree in Computer Science and Engineering Department from A.B.E.S Engineering College, Ghaziabad, India in July 2011. Her research interests include data mining, web mining, deep learning, social networks and wireless sensor networks.

Neetu Sardana

Neetu Sardana is an Associate Professor (Senior Grade) in the Department of Computer Science Engineering at Jaypee Institute of Information Technology. She has done PhD in the area of ‘databases and web’ from Kurukshetra University, KU. Currently, her interest area includes social network analysis, web mining, mining software repositories and XML data indexing. She has many research papers in peer reviewed journals and conferences. She has been actively involved in organising several national and international seminars, and conferences. She had supervised one PhD scholar, ten M.Tech theses and 25 B.Tech major projects. She is currently supervising three PhD scholars and two M.Tech theses.

Raghav Mehta

Raghav Mehta is a Data Scientist in industry. He received his B.Tech degree in Computer Science and Engineering Department at Jaypee Institute of Information Technology, Noida, India. His research interests include block chain architecture, deep learning application, 3D Reconstruction, GIS Processing.