Real-time Recommendation System Research Articles

Deep online recommendations for connected E-taxis by coupling trajectory mining and reinforcement learning

There is a growing interest in the optimization of vehicle fleets management in urban environments. However, limited attention has been paid to the integrated optimization of electric taxi fleets accounting for different operations as well as complex spatiotemporal demand dynamics. To this end, this study develops a real-time recommendation framework based on deep reinforcement learning (DRL) for electric taxis (E-taxis) to improve their system performance with explicit modeling of multiple vehicle actions and varying travel demand across space and over time. Spatiotemporal patterns of urban taxi travels are extracted from large-scale taxi trajectories. Spatiotemporal strategies are proposed to coordinate E-taxis’ repositioning and recharging with optimized recommendation for next destinations and charging stations. A spatiotemporal double deep Q-network (ST-DDQN) is embedded in the DRL framework to maximize the daily profit. A prototype real-time recommendation system for E-taxis is implemented for the decision-making of E-taxi drivers and sensitivity analyses are carried out. The experimental results in Shenzhen, China suggest that the proposed framework could improve the overall performance. This study will benefit the promotion of connected E-taxis and the development of clean and smart transportation.

A Real Time Tourism Recommender System using KNN and RBM Approach

Abstract: Tourism has become a significant contributor to both the industry and national economy. Over the years, the desire to travel and explore new places has led to a substantial increase in the number of tourists. This boom in tourism has resulted in many businesses, both global and local, as well as governments investing heavily in the industry. However, while governments invest in maintaining and promoting tourist attractions, there is often no emphasis on improving the overall experience of tourists.To address this issue, a real-time recommender system can be implemented. This system will provide tourists with recommendations based on their preferences, rather than just providing them with information. As the environment for recommender systems has become increasingly complex and dynamic, with diverse information available in real-time, it is necessary to develop an effective touring recommender system based on real-time characteristics. This system will provide tourists with real-time recommendations, thus enhancing their experience.To achieve this, a recommendation framework that provides comprehensive information for tourists is needed. This framework will guide tourists from the initial stage of exploring which country to visit, to providing a complete comprehensive guide for them once they arrive at their vacation destination. The goal of this solution is to give tourists the best possible experience, eliminating the need to depend on the help of others.Several features will be implemented in this application, such as comprehensive information on places to stay, dine, and visit, using the current location and budget, popularity, and other characteristics. The system will also create a timetable for tourists based on their duration of stay and provide real-time assistance. Overall, the system will provide a personalized and optimized touring experience for the tourist.With the implementation of this recommender system, tourists will be able to make more informed decisions about where to go, what to do, and where to stay. By using real-time data and personalized recommendations, tourists can enjoy a more engaging and satisfying vacation experience. This system will also benefit the tourism industry as a whole, by increasing customer satisfaction and promoting repeat visits

Real-Time Context-Aware Recommendation System for Tourism.

Recently, the tourism trend has been shifting towards the Tourism 2.0 paradigm due to increased travel experiences and the increase in acquiring and sharing information through the Internet. The Tourism 2.0 paradigm requires developing intelligent tourism service tools for positive effects such as time savings and marketing utilization. Existing tourism service tools recommend tourist destinations based on the relationship between tourists and tourist destinations or tourism patterns, so it is difficult to make recommendations in situations where information is insufficient or changes in real time. In this paper, we propose a real-time recommendation system for tourism (R2Tour) that responds to changing situations in real time, such as external factors and distance information, and recommends customized tourist destinations according to the type of tourist. R2Tour trains a machine learning model with situational information such as temperature and precipitation and tourist profiles such as gender and age to recommend the top five nearby tourist destinations. To verify the recommendation performance of R2Tour, six machine learning models, including K-NN and SVM, and information on tourist attractions in Jeju Island were used. As a result of the experiment, R2Tour was verified with accuracy of 77.3%, micro-F1 0.773, and macro-F1 0.415. Since R2Tour trains tourism patterns based on situational information, it is possible to recommend new tourist destinations and respond to changing situations in real time. In the future, R2Tour can be installed in vehicles to recommend nearby tourist destinations or expanded to tasks in the tourism industry, such as a smart target advertising system.

Comparison of Real-Time and Batch Job Recommendations

Collaborative filtering recommendation systems are traditionally trained in a batch manner and are designed to produce personalized recommendations for a large number of users at the same time. However, in many industrial use cases, it is reasonable to produce recommendations in real time, taking account of very recent user interactions. In this work, we present the implementation of batch and real-time recommendation systems using the example of the RP3Beta model, a simple scalable graph-based model that outperforms multiple more advanced models. Our approach can be utilized by any recommendation system if user-to-item recommendations can be obtained based on item-to-item recommendations. We show that it covers multiple common recommendation models, especially collaborative filtering approaches where user features are not available. We also provide the results of A/B tests comparing these two approaches in a real-world scenario of a job recommendation task, conducted with almost 200,000 OLX users. We report at least 10% more users applying for recommended job ads when using a real-time instead of a batch approach. We believe that our results can help other organizations to take informed decisions about whether to make the effort of moving from a batch to a real-time recommendation setting.

A distributed real-time recommender system for big data streams

Recommender Systems (RS) play a crucial role in our lives. As users become continuously connected to the internet, they are less tolerant of obsolete recommendations made by an RS. Online RS has to address three requirements: continuous training and recommendation, handling concept drifts, and the ability to scale. Streaming RS proposed in the literature address the first two requirements only. That is because they run the training process on a single machine.To tackle the third challenge, we propose a Splitting and Replication mechanism for distributed streaming RS. Our mechanism is inspired by the shared-nothing architecture that underpins contemporary big data processing systems. We have applied our mechanism to two well-known approaches for online RS, namely, matrix factorization and item-based collaborative filtering. We conducted experiments comparing the performance with the baseline (single machine). Evaluating different data sets, experiments show online recall improvement by 40% with more than 50% less memory consumption.

Interpretable click-through rate prediction through distillation of the neural additive factorization model

An accurate estimation of the click-through rate (CTR), that is, the probability of clicking on a recommended advertisement item online, is crucial for advertising agencies to make appropriate suggestions to users and maximise their income. However, the existing CTR prediction techniques exhibit two major limitations in estimating accurate CTRs. First, they lack interpretability as they are unable to justify and explain the outcomes of the models. Irrelevant recommendations of products and services may have severe consequences on the personal and financial safety of a user. Second, the high computational complexity of deep-learning models hinders deployment in real-time recommender systems. Thus, this study proposes an interpretable, accurate, and efficient CTR estimator based on the neural additive factorization model (NAFM). The NAFM leverages the model distillation framework, where it effectively learns from a gated ensemble of existing CTR models. The NAFM provides interpretable insights into features and their interactions with a reduced computational cost. The effectiveness and efficiency of the proposed NAFM was verified by applying it on two public click-through datasets, namely, Criteo and Avazu. Unlike post-hoc explainable models, the NAFM avoids an additional phase of training to generate an interpretable model, and its explanations are truthful to the model.

A long command subsequence algorithm for manufacturing industry recommendation systems with similarity connection technology

Abstract The manufacturing industry requires a unique recommendation system to suggest products and raw materials, but its performance is often poor in massive data environment. In order to solve the similarity connection problem of large-scale real-time data, the optimised incremental similarity connection method which is used to deal with streaming data can be used to concisely obtain the longest common additive sequence of two given input sequences. This paper, on the basis of the recursion equation, applies a very simple linear space algorithm to solve this problem and adopts new states to carry out similarity connection of incremental data. The experimental results demonstrate that this method can not only ensure the accuracy of real-time recommendation system but also greatly reduce the computed amount.

A Novel Approach for Product Recommendation Using Smartphone Sensor Data

Human Activity-based studies have become an omnipresent research topic in Machine Learning. Considering the countless impacts of human activity on persons' everyday life, we have analyzed the correlation between human activity and their product preferences in our study and proposed that daily human activity could be a metric for product recommendation models. To address this previously unaccounted phenomenon, a new approach is presented in our study that gives real-time recommendations to users by observing their activeness in daily life. However, product recommendation systems mostly believe in ratings, and the purchase behavior of users instead of investigating the precious insights of users' daily activities. But we examined smartphones' GPS sensor data using machine learning algorithms to urge insights from users' daily activeness and proposed a model for predicting the product of interest of the purchasers, based on the activeness of their daily life. Moreover, based on our model, we have introduced a prototype of a real-time recommendation system, especially for the retail shops that rely on users' implicit data from smartphone sensors to form product recommendations. For conducting our study, we developed an android application that—collects embedded smartphone sensor data and can detect objects to provide product recommendations and product details. Experiment shows, that our proffered daily activeness-based recommendation system using smartphone sensor data, performs with a precision of 66%, but it is also a promising performance because it does not use customers' explicit feedback.

A multi‐preference integrated algorithm for deep learning based recommender framework

SummaryNowadays, the online recommender systems based collaborative filtering methods are widely employed to model long term user preferences (LTUP). The deep learning methods, like recurrent neural networks (RNN) have the potential to model short‐term user preferences (STUP). There is no dynamic integration of these two models in the existing recommender systems. Therefore, in this article, a multi‐preference integrated algorithm (MPIA) for deep learning based recommender framework (DLRF) is proposed to perform the dynamic integration of these two models. Moreover, the MPIA addresses improper data and to improve the performance for creating recommendations. This algorithm is depending on an enhanced long short term memory (LSTM) with additional controllers to consider relative information. Here, experiments are carried out by Amazon benchmark datasets, then obtained outcomes are compared with other existing recommender systems. From the comparison, the experimental outcomes show that the proposed MPIA outperforms existing systems under performance metrics, like area under curve, F1‐score. Consequently, the MPIA can be integrated with real time recommender systems.

A Progressive Review: Emerging Technologies for ADAS Driven Solutions

Over the last decade, the Advanced Driver Assistance System (ADAS) concept has evolved significantly. ADAS involves several technologies such as automotive electronics, vehicle-to-vehicle (V2V) vehicle-to-infrastructure (V2I) communication, RADAR, LIDAR, computer vision, and machine learning. Of these, <i>computer vision</i> and <i>machine learning</i> based solutions have mainly been effective that have allowed real-time vehicle control, driver aided systems, etc. However, most of the existing works deal with the deployment of ADAS and autonomous driving functionality in countries with well-disciplined lane traffic. Nevertheless, these solutions and frameworks do not work in countries and cities with less-disciplined/chaotic traffic. This paper identifies the research gaps, reviews the state-of-the-art looking at the different functionalities of ADAS and its levels of autonomy. Importantly, it provides a detailed description of vision intelligence and computational intelligence for ADAS. The eye-gaze and head pose estimation in vision intelligence is detailed. Notably, the learning algorithms such as supervised, unsupervised, reinforcement learning and deep learning solutions for ADAS are considered and discussed. Significantly, this would enable developing a real-time recommendation system for system-assisted/autonomous vehicular environments with less-disciplined road traffic.

Data Mining-based Real-Time User-centric Recommender System for Nigerian Tourism Industry

The tourism information system in Nigeria is not novel. What is novel is the need to develop reliable real-time recommender systems that can adequately aid tourists in their decisions. Several researchers have proposed various models. However, there are still issues about the applicability, effectiveness, efficiency, and reliability of the existing recommenders in the Nigerian tourism sector. This work is aimed at developing an improved model for real-time tourism recommender in Nigeria based on a data mining model. The objectives include the development of a data mining model for real-time reliable user-centric tourism recommendation and evaluation of the recommender system. To achieve these, a supervised machine learning-based classifier is modelled. The classifier system is evaluated using four thousand (4,000) datasets acquired from online and physical Nigerian tourism sources. Nine machine learning algorithms are compared during the testing process based on accuracy and other standard performance metrics. Experimental results show that the PART algorithm outperforms all other algorithms with an accuracy of 91.65%, F-Measure of 0.917, true positive rate of 0.913, the false-positive rate of 0.029, and the precision of 0.917, and recall of 0.917. In terms of efficiency, it also records the least time-to-model of 0.02 seconds. The rules generated from this algorithm are incorporated into the design of a prototype to test the recommender. The usefulness and efficiency scores based on test cases involving 20 participants prove that the recommender system would be a veritable tool for tourism in Nigeria.

A Long Command Subsequence Algorithm for Manufacturing Industry Recommendation System with Similarity Connection Technology

Manufacturing industry requires a unique recommendation system to suggest products and raw materials, but its performance is often poor in massive data environment. In order to solve the similarity connection problem of large-scale real-time data, the optimized incremental similarity connection method which is used to deal with streaming data can concisely obtain the longest common additive sequence of two given input sequences. This paper, on the basis of the recursion equation, applies a very simple linear space algorithm to solve this problem and adopts new states to carry out similarity connection of incremental data. The experimental results demonstrate that this method can not only ensure the accuracy of real-time recommendation system but also greatly reduce the computed amount.

Preference-Tree-Based Real-Time Recommendation System.

In the current era of online information overload, recommendation systems are very useful for helping users locate content that may be of interest to them. A personalized recommendation system presents content based on information such as a user’s browsing history and the videos watched. However, information filtering-based recommendation systems are vulnerable to data sparsity and cold-start problems. Additionally, existing recommendation systems suffer from the large overhead incurred in learning regression models used for preference prediction or in selecting groups of similar users. In this study, we propose a preference-tree-based real-time recommendation system that uses various tree models to predict user preferences with a fast runtime. The proposed system predicts preferences based on two balance constants and one similarity threshold to recommend content with a high accuracy while balancing generalized and personalized preferences. The results of comparative experiments and ablation studies confirm that the proposed system can accurately recommend content to users. Specifically, we confirmed that the accuracy and novelty of the recommended content were, respectively, improved by 12.1% and 27.2% compared to existing systems. Furthermore, we verified that the proposed system satisfies real-time requirements and mitigates both cold-start and overfitting problems.

DistilledCTR: Accurate and scalable CTR prediction model through model distillation

Accuracy and scalability are critical to the efficiency and effectiveness of real-time recommender systems. Recent deep learning-based click-through rate prediction models are improving in accuracy but at the expense of computational complexity. The purpose of this study is to propose an accurate and scalable click-through rate (CTR) prediction model for real-time recommendations. This study investigates the complexity, accuracy, and scalability aspects of various CTR models. This work ensembles top CTR models using a gated network and distill into a deep neural network (DNN) using a knowledge distillation framework. Distilled DNN model is more accurate and 20x scalable than any of the individual CTR models. The low latency of distilled model makes it scalable and fit for deployment in real-time recommender systems. The proposed distillation framework is extensible to integrate any CTR models to the ensemble and can be distilled to any neural architecture.

Location-Aware Real-Time Recommender Systems for Brick-and-Mortar Retailers

Providing real-time product recommendations based on consumer profiles and purchase history is a successful marketing strategy in online retailing. However, brick-and-mortar (BAM) retailers have yet to utilize this important promotional strategy because it is difficult to predict consumer preferences as they travel in a physical space but remain anonymous and unidentifiable until checkout. In this paper, we develop such a recommender approach by leveraging the consumer shopping path information generated by radio frequency identification technologies. The system relies on spatial-temporal pattern discovery that measures the similarity between paths and recommends products based on measured similarity. We use a real-world retail data set to demonstrate the feasibility of this real-time recommender system and show that our approach outperforms benchmark methods in key recommendation metrics. Conceptually, this research provides generalizable insights on the correlation between spatial movement and consumer preference. It makes a strong case that the emerging location and path data and the spatial-temporal pattern discovery methods can be effectively utilized for implementable marketing strategies. Managerially, it provides one of the first real-time recommender systems for BAM retailers. Our approach can potentially become the core of the next-generation intelligent shopping environment in which the stores customize marketing efforts to provide real-time, location-aware recommendations.

Securing industrial communication with software-defined networking.

Industrial Cyber-Physical Systems (CPSs) require flexible and tolerant communication networks to overcome commonly occurring security problems and denial-of-service such as links failure and networks congestion that might be due to direct or indirect network attacks. In this work, we take advantage of Software-defined networking (SDN) as an important networking paradigm that provide real-time fault resilience since it is capable of global network visibility and programmability. We consider OpenFlow as an SDN protocol that enables interaction between the SDN controller and forwarding plane of network devices. We employ multiple machine learning algorithms to enhance the decision making in the SDN controller. Integrating machine learning with network resilience solutions can effectively address the challenge of predicting and classifying network traffic and thus, providing real-time network resilience and higher security level. The aim is to address network resilience by proposing an intelligent recommender system that recommends paths in real-time based on predicting link failures and network congestions. We use statistical data of the network such as link propagation delay, the number of packets/bytes received and transmitted by each OpenFlow switch on a specific port. Different state-of-art machine learning models has been implemented such as logistic regression, K-nearest neighbors, support vector machine, and decision tree to train these models in normal state, links failure and congestion conditions. The models are evaluated on the Mininet emulation testbed and provide accuracies ranging from around 91-99% on the test data. The machine learning model with the highest accuracy is utilized in the intelligent recommender system of the SDN controller which helps in selecting resilient paths to achieve a better security and quality-of-service in the network. This real-time recommender system helps the controller to take reactive measures to improve network resilience and security by avoiding faulty paths during path discovery and establishment.

An effective recommender system based on personality traits, demographics and behavior of customers in time context

PurposeImproving the performance of recommender systems (RSs) has always been a major challenge in the area of e-commerce because the systems face issues such as cold start, sparsity, scalability and interest drift that affect their performance. Despite the efforts made to solve these problems, there is still no RS that can solve or reduce all the problems simultaneously. Therefore, the purpose of this study is to provide an effective and comprehensive RS to solve or reduce all of the above issues, which uses a combination of basic customer information as well as big data techniques.Design/methodology/approachThe most important steps in the proposed RS are: (1) collecting demographic and behavioral data of customers from an e-clothing store; (2) assessing customer personality traits; (3) creating a new user-item matrix based on customer/user interest; (4) calculating the similarity between customers with efficient k-nearest neighbor (EKNN) algorithm based on locality-sensitive hashing (LSH) approach and (5) defining a new similarity function based on a combination of personality traits, demographic characteristics and time-based purchasing behavior that are the key incentives for customers' purchases.FindingsThe proposed method was compared with different baselines (matrix factorization and ensemble). The results showed that the proposed method in terms of all evaluation measures led to a significant improvement in traditional collaborative filtering (CF) performance, and with a significant difference (more than 40%), performed better than all baselines. According to the results, we find that our proposed method, which uses a combination of personality information and demographics, as well as tracking the recent interests and needs of the customer with the LSH approach, helps to improve the effectiveness of the recommendations more than the baselines. This is due to the fact that this method, which uses the above information in conjunction with the LSH technique, is more effective and more accurate in solving problems of cold start, scalability, sparsity and interest drift.Research limitations/implicationsThe research data were limited to only one e-clothing store.Practical implicationsIn order to achieve an accurate and real-time RS in e-commerce, it is essential to use a combination of customer information with efficient techniques. In this regard, according to the results of the research, the use of personality traits and demographic characteristics lead to a more accurate knowledge of customers' interests and thus better identification of similar customers. Therefore, this information should be considered as a solution to reduce the problems of cold start and sparsity. Also, a better judgment can be made about customers' interests by considering their recent purchases; therefore, in order to solve the problems of interest drifts, different weights should be assigned to purchases and launch time of products/items at different times (the more recent, the more weight). Finally, the LSH technique is used to increase the RS scalability in e-commerce. In total, a combination of personality traits, demographics and customer purchasing behavior over time with the LSH technique should be used to achieve an ideal RS. Using the RS proposed in this research, it is possible to create a comfortable and enjoyable shopping experience for customers by providing real-time recommendations that match customers' preferences and can result in an increase in the profitability of e-shops.Originality/valueIn this study, by considering a combination of personality traits, demographic characteristics and time-based purchasing behavior of customers along with the LSH technique, we were able for the first time to simultaneously solve the basic problems of CF, namely cold start, scalability, sparsity and interest drift, which led to a decrease in significant errors of recommendations and an increase in the accuracy of CF. The average errors of the recommendations provided to users based on the proposed model is only about 13%, and the accuracy and compliance of these recommendations with the interests of customers is about 92%. In addition, a 40% difference between the accuracy of the proposed method and the traditional CF method has been observed. This level of accuracy in RSs is very significant and special, which is certainly welcomed by e-business owners. This is also a new scientific finding that is very useful for programmers, users and researchers. In general, the main contributions of this research are: 1) proposing an accurate RS using personality traits, demographic characteristics and time-based purchasing behavior; 2) proposing an effective and comprehensive RS for a “clothing” online store; 3) improving the RS performance by solving the cold start issue using personality traits and demographic characteristics; 4) improving the scalability issue in RS through efficient k-nearest neighbors; 5) Mitigating the sparsity issue by using personality traits and demographic characteristics and also by densifying the user-item matrix and 6) improving the RS accuracy by solving the interest drift issue through developing a time-based user-item matrix.

A clinical coding recommender system

Clinical coding of hospital admissions can erroneously omit diagnosis and procedure codes. A consequence of these omissions is that the condition and treatment of the patient are not fully captured by the entered codes, which can then also impact hospital revenue. One way to prevent these errors is through a real-time recommender system which suggests the addition of codes at the point of coding when it appears they have been omitted. Association analysis uncovers patterns between codes, forming a basis for coding recommendations. Combining association analysis with manual expert validation produces more useful recommendations (we refer to this as the expert validated list), but is labour-intensive. In this study, we propose an approach using Bayesian Networks to determine the conditional relationships between codes. Performance is evaluated using a testing strategy which simulates errors through the random removal of codes from episodes of patient care and counts how many of the removed codes are recommended to coders by each recommender. Performance is also based on how many recommended codes were not removed (superfluous recommendations) which we seek to minimise. We develop a recommender system which generates 96% of the number of correct recommendations produced by the expert validated list, while having 68% fewer superfluous recommendations. Our proposed methodology provides a high performance recommender while reducing dependence on labour-intensive effort by clinical coding experts.

Tree-Based Real-Time Advertisement Recommendation System in Online Broadcasting

The viewing time of media content per week through TV is still dominant. Users are exposed to numerous advertisements, such as commercials, electronic home shopping, product placement (PPL), and T-Commerce while watching TV programs. Most of the advertisement systems provide a good overview of products. However, traditional advertising services do not consider user preferences, meaning it is difficult to expect anything more than mere exposure to them. We can adopt a recommendation system to predict the preference. However, existing recommendation systems find it difficult to satisfy the real-time requirements of online broadcasting because of the large overhead incurred in preference prediction processes. In this paper, we propose a real-time recommendation system to provide personalized advertisements. The proposed system generates tree models based on user historical data. To reduce the overhead of preference prediction, we introduce a sorted HashMap that enables fast tree searches. For sophisticated preference prediction, the proposed system normalizes the users' preferences by considering the characteristics of their tree model. Finally, we conduct experiments to evaluate the performance of the proposed tree-based recommendation system.

Online discrete choice models: Applications in personalized recommendations

This paper presents a framework for estimating and updating user preferences in the context of app-based recommender systems. We specifically consider recommender systems which provide personalized menus of options to users. A Hierarchical Bayes procedure is applied in order to account for inter- and intra-consumer heterogeneity, representing random taste variations among individuals and among choice situations (menus) for a given individual, respectively. Three levels of preference parameters are estimated: population-level, individual-level and menu-specific. In the context of a recommender system, the estimation of these parameters is repeated periodically in an offline process in order to account for trends, such as changing market conditions. Furthermore, the individual-level parameters are updated in real-time as users make choices in order to incorporate the latest information from the users. This online update is computationally efficient which makes it feasible to embed it in a real-time recommender system. The estimated individual-level preferences are stored for each user and retrieved as inputs to a menu optimization model in order to provide recommendations. The proposed methodology is applied to both Monte-Carlo and real data. It is observed that the online update of the parameters is successful in improving the parameter estimates in real-time. This framework is relevant to various recommender systems that generate personalized recommendations ranging from transportation to e-commerce and online marketing, but is particularly useful when the attributes of the alternatives vary over time.