Factorizing Historical User Actions for Next-Day Purchase Prediction

It is common practice for many large e-commerce operators to analyze daily logged transaction data to predict customer purchase behavior, which may potentially lead to more effective recommendations and increased sales. Traditional recommendation techniques based on collaborative filtering, although having gained success in video and music recommendation, are not sufficient to fully leverage the diverse information contained in the implicit user behavior on e-commerce platforms. In this article, we analyze user action records in the Alibaba Mobile Recommendation dataset from the Alibaba Tianchi Data Lab, as well as the Retailrocket recommender system dataset from the Retail Rocket website. To estimate the probability that a user will purchase a certain item tomorrow, we propose a new model called Time-decayed Multifaceted Factorizing Personalized Markov Chains (Time-decayed Multifaceted-FPMC), taking into account multiple types of user historical actions not only limited to past purchases but also including various behaviors such as clicks, collects and add-to-carts. Our model also considers the time-decay effect of the influence of past actions. To learn the parameters in the proposed model, we further propose a unified framework named Bayesian Sparse Factorization Machines. It generalizes the theory of traditional Factorization Machines to a more flexible learning structure and trains the Time-decayed Multifaceted-FPMC with the Markov Chain Monte Carlo method. Extensive evaluations based on multiple real-world datasets demonstrate that our proposed approaches significantly outperform various existing purchase recommendation algorithms.

Multipath Wireless Network Coding: A Scheduling Constraint in Game Perspective

This paper considers wireless networks in which various paths are obtainable involving each source and destination. It is allowing each source to tear traffic among all of its existing paths, and it may conquer the lowest achievable number of transmissions per unit time to sustain a prearranged traffic matrix. Traffic bound in contradictory instructions in excess of two wireless hops can utilize the “reverse carpooling” advantage of network coding in order to decrease the number of transmissions used. These call such coded hops “hyper-links.” With the overturn carpooling procedure, longer paths might be cheaper than shorter ones. However, convenient is an irregular situation among sources. The network coding advantage is realized only if there is traffic in both directions of a shared path. This project regard as the problem of routing amid network coding by egotistic agents (the sources) as a potential game and develop a method of state-space extension in which extra agents (the hyper-links) decouple sources’ choices from each other by declaring a hyper-link capacity, allowing sources to split their traffic selfishly in a distributed fashion, and then altering the hyper-link capacity based on user actions. Furthermore, each hyper-link has a scheduling constraint in stipulations of the maximum number of transmissions authorized per unit time. Finally these project show that our two-level control scheme is established and verify our investigative insights by simulation.

The Effect of Visuomotor Latency on Steering Behavior in Virtual Reality

Visual feedback latency in virtual reality systems is inherent due to the computing time it takes to simulate the effects of user actions. Depending upon the nature of interaction and amount of latency, the impact of this latency could range from a minor degradation to a major disruption of performance. The goal of this study was to examine how visuomotor latency impacts users’ performance in a continuous steering task and how users adapt to this latency with experience. The task involved steering a bike along an illuminated path in a dark environment viewed in an HTC Vive head-mounted virtual reality display. We examined how users adapt to visuomotor latency in two different conditions: 1) when the user controlled the steering while the bike moved forward at a constant speed, and 2) when the user controlled the steering and the speed of the bike through pedaling and braking. We found that users in both conditions started with a large steering error at the beginning of exposure to visuomotor latency but then quickly adapted to the delay. We also found that when users could control their speed, they adjusted their speed based on the complexity of the path (i.e., proximity to turns) and they gradually increased their speed as they adapted to latency and gained better control over their movement. The current work supports the idea that users can adapt to visual feedback delay in virtual reality regardless of whether they control the pace of movement. The results inform the design of virtual reality simulators and teleoperation systems and give insight into perceptual-motor adaptation in the presence of latency.

SessNet: A Hybrid Session-Based Recommender System

<div>Session-based recommendation is the task of predicting user actions during short online sessions. Previous work considers the user to be anonymous in this setting, with no past behavior history available. In reality, this is often not the case, and none of the existing approaches are flexible enough to seamlessly integrate user history when available. In this thesis, we propose a novel hybrid session-based recommender system to perform next-click prediction, which is able to take advantage of historical user preferences when accessible. Specifically, we propose SessNet, a deep profiling session-based recommender system, with a two-stage dichotomy. First, we use bidirectional transformers to model local and global session intent. Second, we concatenate any user information with the current session representation to feed to a feed-forward neural network to identify the next click. Historical user preferences are computed using the sequence-aware embeddings obtained from the first step, allowing us to better understand the users. We evaluate the efficacy of the proposed method using two benchmark datasets, YooChoose1/64 and Dignetica. Our experimental results show that SessNet outperforms state-of-the-art session-based recommenders on P@20 for both datasets.</div>

SessNet: A Hybrid Session-Based Recommender System

<div>Session-based recommendation is the task of predicting user actions during short online sessions. Previous work considers the user to be anonymous in this setting, with no past behavior history available. In reality, this is often not the case, and none of the existing approaches are flexible enough to seamlessly integrate user history when available. In this thesis, we propose a novel hybrid session-based recommender system to perform next-click prediction, which is able to take advantage of historical user preferences when accessible. Specifically, we propose SessNet, a deep profiling session-based recommender system, with a two-stage dichotomy. First, we use bidirectional transformers to model local and global session intent. Second, we concatenate any user information with the current session representation to feed to a feed-forward neural network to identify the next click. Historical user preferences are computed using the sequence-aware embeddings obtained from the first step, allowing us to better understand the users. We evaluate the efficacy of the proposed method using two benchmark datasets, YooChoose1/64 and Dignetica. Our experimental results show that SessNet outperforms state-of-the-art session-based recommenders on P@20 for both datasets.</div>

System End-User Actions as aThreat to Information System Security

Information system security is of paramount importance to every institution that deals with digital information. Nowadays, efforts to address cybersecurity issues are mostly software or hardware-oriented. However, the most common types of cybersecurity breaches happen as a result of unintentional human errors also known as end user actions. Thus, this study aimed to identify the end-user errors and the resulting vulnerabilities that could affect the system security requirements, the CIA triad of information assets. The study further presents state-of-the-art countermeasures and intellectual ideas on how entities can protect themselves from advent events. Adopted is a mixed-method research approach to inform the study. A closed-ended questionnaire and semi-structured interviews were used as data collection tools. The findings of this study revealed that system end user errors remain the biggest threat to information systems security. Indeed errors make information systems vulnerable to certain cybersecurity attacks and when exploited puts legitimate users at risk.

Learning intents behind interactions with high-order graph for session-based intelligent recommendation

Session-based recommendation is an overwhelming task owing to the inherent ambiguity in anonymous behaviors. Graph convolutional neural networks are receiving wide attention for session-based recommendation research for the sake of their ability to capture the complex transitions of interactions between sessions. Recent research on session-based recommendations mainly focuses on sequential patterns by utilizing graph neural networks. However, it is undeniable that proposed methods are still difficult to capture higher-order interactions between contextual interactions in the same session and has room for improvement. To solve it, we propose a new method based on graph attention mechanism and target oriented items to effectively propagate information, HOGAN for brevity. Higher-order graph attention networks are used to select the importance of different neighborhoods in the graph that consists of a sequence of user actions for recommendation applications. The complementarity between high-order networks is adopted to aggregate and propagate useful signals from the long distant neighbors to solve the long-range dependency capturing problem. Experimental results consistently display that HOGAN has a significantly improvement to 71.53% on precision for the Yoochoose1_64 dataset and enhances the property of the session-based recommendation task.

Scenario model of intelligent decision support based user digital life models

Introduction. In the decision support domain, the practice of using information from user digital traces has not been widespread so far. Earlier, the authors of this paper developed a conceptual framework of intelligent decision support based on user digital life models that was aimed at recommending decisions using information from the user digital traces. The present research is aiming at the development of a scenario model that implements this framework. Purpose: the development of a scenario model of intelligent decision support based on user digital life models and an approach to grouping users with similar preferences and decision-making behaviours. Results: A scenario model of intelligent decision support based on user digital life models has been developed. The model is intended to recommend to the user decisions based on the knowledge about the user decision-maker type, decision support problem, and problem domain. The scenario model enables to process incompletely formulated problems due to taking into account the preferences of users who have preferences and decision-making behaviour similar to the active user. An approach to grouping users with similar preferences and decision-making behaviours has been proposed. The approach enables to group users with similar preferences and decision-making behaviours based on the information about user behavioural segments that exist in various domains, behavioural segmentation rules, and user actions represented in their digital life models. Practical relevance: the research results are beneficial for the development of advanced recommendation systems expected to tracking digital traces.