0000000000007004
AUTHOR
Gaurav Pandey
Vectors of Pairwise Item Preferences
Neural embedding has been widely applied as an effective category of vectorization methods in real-world recommender systems. However, its exploration of users’ explicit feedback on items, to create good quality user and item vectors is still limited. Existing neural embedding methods only consider the items that are accessed by the users, but neglect the scenario when a user gives high or low rating to a particular item. In this paper, we propose Pref2Vec, a method to generate vector representations of pairwise item preferences, users and items, which can be directly utilized for machine learning tasks. Specifically, Pref2Vec considers users’ pairwise item preferences as elementary units. …
Identifying Images with Ladders Using Deep CNN Transfer Learning
Deep Convolutional Neural Networks (CNNs) as well as transfer learning using their pre-trained models often find applications in image classification tasks. In this paper, we explore the utilization of pre-trained CNNs for identifying images containing ladders. We target a particular use case, where an insurance firm, in order to decide the price for workers’ compensation insurance for its client companies, would like to assess the risk involved in their workplace environments. For this, the workplace images provided by the client companies can be utilized and the presence of ladders in such images can be considered as a workplace hazard and therefore an indicator of risk. To this end, we e…
Gaming Bot Detection: A Systematic Literature Review
In online games, some players employ programs (bots) that allow them to bypass game routines and effortlessly gain virtual resources. This practice leads to negative effects, such as reduced revenue for the game development companies and unfair treatment for ordinary players. Bot detection methods act as a counter measure for such players. This paper presents a systematic literature review of bot detection in online games. We mainly focus on games that allow resource accumulation for players between game sessions. For this, we summarize the existing literature, list categories of games ignored by the scientific community, review publicly available datasets, present the taxonomy of detection…
Listwise Recommendation Approach with Non-negative Matrix Factorization
Matrix factorization (MF) is one of the most effective categories of recommendation algorithms, which makes predictions based on the user-item rating matrix. Nowadays many studies reveal that the ultimate goal of recommendations is to predict correct rankings of these unrated items. However, most of the pioneering efforts on ranking-oriented MF predict users’ item ranking based on the original rating matrix, which fails to explicitly present users’ preference ranking on items and thus might result in some accuracy loss. In this paper, we formulate a novel listwise user-ranking probability prediction problem for recommendations, that aims to utilize a user-ranking probability matrix to predi…
Finding Tours for a Set of Interests
This paper addresses a novel tour discovery problem in the domain of travel search. We create a ranking of tours for a set of travel interests, where a tour is a group of city documents and a travel interest is a query. While generating and ranking tours, it is aimed that each interest (from the interest set) is satisfied by at least one city in a tour and the distance traveled to cover the tour is not too large. Firstly, we generate tours for the interest set, by utilizing the available ranking of cities for the individual interests and the distances between the cities. Then, in absence of existing methods directly related to our problem, we devise our novel techniques to calculate ranking…
CitySearcher: A City Search Engine For Interests
We introduce CitySearcher, a vertical search engine that searches for cities when queried for an interest. Generally in search engines, utilization of semantics between words is favorable for performance improvement. Even though ambiguous query words have multiple semantic meanings, search engines can return diversified results to satisfy different users' information needs. But for CitySearcher, mismatched semantic relationships can lead to extremely unsatisfactory results. For example, the city Sale would incorrectly rank high for the interest shopping because of semantic interpretations of the words. Thus in our system, the main challenge is to eliminate the mismatched semantic relationsh…
Linear Feature Extraction for Ranking
We address the feature extraction problem for document ranking in information retrieval. We then propose LifeRank, a Linear feature extraction algorithm for Ranking. In LifeRank, we regard each document collection for ranking as a matrix, referred to as the original matrix. We try to optimize a transformation matrix, so that a new matrix (dataset) can be generated as the product of the original matrix and a transformation matrix. The transformation matrix projects high-dimensional document vectors into lower dimensions. Theoretically, there could be very large transformation matrices, each leading to a new generated matrix. In LifeRank, we produce a transformation matrix so that the generat…
Recommending Serendipitous Items using Transfer Learning
Most recommender algorithms are designed to suggest relevant items, but suggesting these items does not always result in user satisfaction. Therefore, the efforts in recommender systems recently shifted towards serendipity, but generating serendipitous recommendations is difficult due to the lack of training data. To the best of our knowledge, there are many large datasets containing relevance scores (relevance oriented) and only one publicly available dataset containing a relatively small number of serendipity scores (serendipity oriented). This limits the learning capabilities of serendipity oriented algorithms. Therefore, in the absence of any known deep learning algorithms for recommend…