Department of Computer Science
Permanent URI for this communityhttps://repository.cuilahore.edu.pk/handle/123456789/16
Browse
13 results
Search Results
Item Repeated Buyer Prediction: A Study of Repurchasing Intention of Buyer in E Commerce(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Muhammad Usman; SP20-RCS-014; Dr. Hamid Turab Mirza; LHR TP 8358During promotions, retailers frequently obtain a huge number of new customers. However, several of the purchasers attracted are one-time hunters, and the deals are unlikely to have a long-term influence on sales. It was critical for merchants to discover who may be turned into regular loyal consumers and afterward target them to reduce promotion costs and boost return on investment (ROI). It was critical for merchants to discover who could be converted into repeat customers to solve this problem. Merchants may significantly cut promotion costs and increase the return on that investment by focusing on these prospective loyal consumers (ROI). Consumer targeting in the area of internet advertising was generally known to be difficult, especially for first-time consumers. In this work, collect a collection of merchants as well as their associated new buyers gained during the "Double 11" day offer using Tmall.com's long-term user behavior record. This experiment objective was to predict whether new clients would become loyal consumers in the future for certain merchants. In other words, this experiment must estimate the probability, which these new purchasers will buying within the similar merchants again for the next six months. This work suggested employing enhanced merged models (XGBoost as well as LightGBM and Histogram-based gradient boosting machine to forecast a repeat customer and feature engineering through extracting feasible features by which important components would be derived to train the model to prophesy the repeated buyer. These experimental findings suggest that when compared to the original models, this work-combined model may achieve significant performance increases. XGBoost accuracy was 95.97 and AUC was 0.9753. The accuracy of Light GBM was 92.58% and the AUC was 96.15%. Histogram-based gradient boosting machine training accuracy was 96.7% and the testing accuracy was 96.27%.Item A Deep Learning Based Prediction of Stock Market Trend using Social Medi(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Aroma Javed; FA20-RCS-006/; LHR TP 8339; Dr. Hamid Turab MirzaMachine learning and deep learning are becoming more and more effective techniques for evaluating financial data, encompassing textual, statistical, and digital information. Future stock prediction is a prominent and challenging deep learning topic in the industry. The difficulty in predicting future stock market stems from too many diverse elements that simultaneously influence the amplitude and frequency of stock market rise and falls. In this research work, the main focus is on the problem of stock market trends predictions using social media as a tool. Digital networks are a fast-growing area of information on the Internet. Perhaps one of the most important features is the instant availability of more knowledge and the users' ability to converse swiftly. Different Deep Learning algorithms (like CNN, RNN, GRU, and Bi Directional RNN) were used to forecast stock market trends based on information from social media, as this data might influence investor behavior. Algorithms were used to investigate the impact of social media accounts on stock market prediction performance. The dataset chosen was an expert and public Twitter post from two prominent technology firms, Alphabet Inc. (Google) and Apple Inc, and news data related to these famous firms. The thesis employed deep learning methods, a pre trained language model for economic sentiment analysis, to extract sentiments from tweets. With the help of this research, it will become easy for an investor to invest his money in companies whose stock market values are high on the basis of sentiment classification and will not lead them to any financial crises. SMP aims to anticipate how the stock value of an economic trade will fluctuate in the foreseeable. If shareholders can precisely estimate stock market progression, investors will indeed be able to turn a profit. Finally, the study predicted the trends by modeling the Data on the proposed GRU model, which outperforms the result of other algorithms. The GRU model has shown significant results with an accuracy of 82.41%.Item A Study of Crime Analysis and Prediction using Data Mining Techniques(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Syed Huzaifa Ansar; FA19-RCS-030; LHR TP 8338; Dr. Hamid Turab MirzaCrime is considered an offense in the social or moral values of a society, due to the constant increase in crimes the safety and security of people in the world are at high risk, because of the severity of this problem, crime analysis is one of the most highlighted research topics from the past few years. In criminology, data mining plays a major role as data mining is a way to discover hidden patterns among the dataset. Researchers are trying to get useful insights for crime prediction by training different machine learning models from real-world data, although a lot of efforts have been made in this context. But most of the models cannot still predict the crime and crime variables such as crime location, date and time. This process becomes even more complex and time-consuming when trying to predict the crime variables. In short, the main goal of this study is to narrow down this gap by developing a system for crime analysis and prediction by using state-of-the-art data mining techniques. In this study, three different deep learning models including Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) with LSTM layers hybrid model, and Bidirectional Long Short Term Memory (Bi-LSTM) are used to perform a time-series analysis of Chicago Crime dataset from 2001 to 2022. The District-wise time series analysis is performed on the number of crimes for a Month, Week, Day, and night. Mean Square Error (RMSE) and Mean Absolute Error (MAE) are used as evaluation measures to evaluate the performance of models. After the experimentation, results showed that the BILSTM model obtained the best results for the District wise predictions of crimes on the Chicago dataset. The results indicated that the BILSTM model gives the highest performance results (MSE = 7.16, MAE = 2.01) and outperformed all other models in forecasting crimes by day.Item Predicting Tourist Destinations based on Interests and Travel Backgrounds using Text Analytics(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) ANAM KHURSHID; FA20-RCS-001; LHR TP 8050; Dr. Hamid Turab MirzaTourist destination prediction has arisen as a new topic within text analytics because of the growing adoption of social media. Tourist data is always beneficial to tourism management since it allows them to give personalized services, products, and destinations to future guests. In predicting tourist destinations, machine learning plays a significant role as it is a way to discover hidden patterns among the dataset; researchers have attempted to get valuable understandings by using data from the real world to train models. Many efforts have been made in this regard; however, most of the models still cannot precisely forecast the tourist’s preferences for destinations. In short, the purpose of this study is to narrow down this gap by introducing a system that uses standard machine learning algorithms to forecast destinations chosen by tourists according to their interests and travel histories. This study extracts a dataset from the CouchSurfing.com website to identify the correlation between tourists' interests and travel backgrounds. The data consists of 9575 records of Pakistan users' profile information. To develop a system with standard accuracy, destinations were divided into 8 regions using Google, and interests were divided into 11 categories using the Yahoo category. Using K-means, clustering has been used several times in this study. This research aims to use classification algorithms to cluster the dataset to identify which interests relate to which countries or regions including KNN, Random Forest, AdaBoost, Gradient Boosting, and LDA. After a comparative results analysis of machine learning algorithms, this research found Gradient Boosting has performed best in classification with the highest accuracy of 99.74% and a kappa Score is 0.99. In the end, the system has successfully predicted tourist destinations related to their interests and past travel experiences. The visitors’ interests according to their destination selections have hardly been studied. This research takes a unique strategy from previous studies in that it focuses on this relationship. For text analysis and future travel destination data, the system has also shown good accuracy and surprising results. As a result, it may help travel companies to build marketing plans for tourists with particular interest categories by offering and advertising places.Item A POI Clustered Users Recommendation Method in LBSNs Considering the Weather Forecast(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Khurram Shahzad; FA19-RCS-023; Dr. Hamid Turab MirzaThe Location-Based Social Network (LBSN) is one type of social web platform that allows users to register when they visit certain Points of Interest (POIs). The practice of recommending points of interest (POI) has become an important component of location-based social networks. However, due to the unique limits such as privacy concerns, accuracy, and reliability, and lack of comprehensive POI coverage of these networks, it remains a difficult challenge. In this thesis, data mining methods (i.e., model-based approach) are applied to handle the problem of the POI recommendation system. The approach is based on a particular method of analyzing geographic data. POI recommendations have a hard time (because of limited context information, credibility concerns, and lack of personalization) persuading users to visit the suggested destinations. The major purpose of this study is to categorize locations into different areas and to use the user group check-ins to train the model to forecast the weather using classification models. In this study, two datasets including Foursquare Check-Ins Tokyo Dataset, and Foursquare Check-Ins New York Dataset are used which contain the check-ins of different locations in New York and Tokyo from 2012-2016. The user’s check-in history is used in terms of timestamps, longitude, latitude, and user behavior to analyze the reliably forecast of the user’s location weather. After applying the data mining methods, the results demonstrate that for the New York check-in corpus, the decision tree method obtained the top performance with an accuracy of 0.74. Regarding the Tokyo check-in corpus, the overall performance indicates that the decision tree algorithm achieved the maximum accuracy of 0.84. The results concerning weather classification show that random forest achieved the best performance with an accuracy of 0.95Item Spam Review Detection through Behavioral and Linguistic Approaches(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Naveed Hussain; FA15-PCS-002; LHR TP 7730Online reviews regarding different products or services have become the main source to determine public opinions. Consequently, manufacturers and sellers are ex tremely concerned with customer reviews as these have a direct impact on their busi nesses. Unfortunately, to gain profits or fame, spam reviews are written to promote or demote targeted products or services. This practice is known as review spamming. In last few years, the Spam Review Detection (SRD) problem has gained much attention from communities and researchers, but there is still a need to introduce new spam re view detection methods to improve accuracy results utilizing real-world datasets. To overcome these problems, three methods have been proposed. In the first framework, two different spam review detection methods have been pro posed: (i) Spam Review Detection using Behavioral Method (SRD-BM) utilizes thir teen different spammer’s behavioral features to calculate the review spam score which is then used to identify spammers and spam reviews, and (ii) Spam Review Detection using Linguistic Method (SRD-LM) works on the content of the reviews and utilizes transformation, feature selection and classification to identify the spam reviews. Exper imental evaluations are conducted on a real-world Amazon review dataset which ana lyzes 26.7 million reviews and 15.4 million reviewers. The evaluations show that both proposed methods have significantly improved the detection process of spam reviews. Specifically, SRD-BM achieved 93.1% accuracy whereas SRD-LM achieved 88.5% accuracy in spam review detection. Comparatively, SRD-BM achieved better accuracy because it works on utilizing a rich set of spammers’ behavioral features of review da taset which provides in-depth analysis of spammer behavior. Moreover, both proposed methods outperformed existing approaches when compared in terms of accurate iden tification of spam reviews. To the best of the researcher’ knowledge, this is the first study of its kind which uses a large-scale review dataset to analyze different spammers’ behavioral features and linguistic methods utilizing different available classifiers. xi The second method has been developed to analyze the Roman Urdu review dataset based on different classification techniques utilizing linguistic and behavioral features. The performance of each classifier is evaluated in several perspectives: (i) Linguistic features are used to calculate accuracy (F1 Score) of each classifier; (ii) Behavioral features combined with distributional and non-distributional aspects are used to evalu ate accuracy (F1 Score) of each classifier; and (iii) The combination of both linguistic and behavioral features (distributional and non-distributional aspects) are used to eval uate the accuracy of each classifier. The experimental evaluations demonstrated an im proved accuracy (F1 Score: 0.96), which is the result of combinations of linguistic fea tures and behavioral features with the distributional aspect of reviewers. Moreover, be havioral features using distributional characteristic achieved an accuracy (F1 Score) of 0.86 and linguistic features shows an accuracy (F1 Score) of 0.69. The outcome of this research can be used to increase customers’ confidence on online reviews in the South Asian region. It can also help to reduce spam reviews in the South Asian region, partic ularly in Pakistan. The third method proposed Spammer Group Detection (SGD) method, which iden tifies suspicious spammer groups based on the similarity of all reviewer’s activities. Deep learning classifiers are used for training and testing the proposed SGD method. The study also proposed the Diversified Set of Reviews (DSR) method which presents a diversified set of top-k non-spam reviews having positive, negative, and neutral sen timents. Furthermore, it covers all possible features about the product or service. Ex perimental evaluations are conducted on daraz.pk and yelp.com real-world review da tasets. It has been observed by experimental analysis that the proposed SGD method has achieved 89.41% accuracy for the Yelp dataset and 81.31% accuracy for the Daraz dataset in detecting suspicious spammer groups and spam reviews.Item Understanding User Mobility Behaviour: A Study of Check-in Patterns in Location-Based Social Networks(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Sajeel Ur Rehman; FA17-RCS-014; LHR TP 7297; Dr. Hamid Turab MirzaIncreasingly there is a tendency amongst social media users to ‘check-in’ i.e., an action allowing individuals to share their location at any given time, to places they physically visit through various social media applications like Facebook, Foursquare, etc. Statistics from these applications serve as a huge reservoir of user data which can be used to understand and predict the mobility behaviour of these users through formulation of a recommender system. The two basic methods for developing such a recommender system are memory-based and model-based system. Owing to pronounced limitations of the memory-based system such as the provision of a huge amount of data being essential for effective performance, this work develops a recommender system using model-based method. User mobility data of New York and Tokyo city (collected over 10 months) is obtained from Foursquare.com. This data is utilized to decipher the mobility behaviour of users: ‘checking-in’ to parks, hotels, recreational centres etc. This data only contains time stamps against the ‘checked-in’ locations. To develop a nuanced recommendation system, further parameters are added qualifying these ‘check-ins’ so that more personalized and precise recommendations are furthered. Firstly, the data is enriched by adding weather as an additional parameter. Secondly, Deep Neural Network” (DNN) is formed by embedding features which are then used to develop the DNN Model. Thirdly, model’s generalization is evaluated through Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Square Error (MSE). Based on these evaluations, after testing, it is concluded that MAE produced best result which is only 1.25 on the dataset and value for RMSE is 1.45 which is second best. Moreover, MSE results are not satisfactory being 2.11. It is anticipated that this recommender system will help local e-commerce and other non-e-commerce venues of the region to increase the visibility of their products or services sales by attracting customers through this developed modelItem Long and Short Term User Preference Learning for Next POI Recommendation(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Muhammad Umair Khalid; SP19-RCS-005; LHR TP 7299; Dr. Hamid Turab MirzaRecommendation systems in the latest years have play an essential part and it is becoming an emerging trend in daily life and business. The Point-of Interest (POI) - recommendation depends on the check-in histories of individual users at an explicit time. The goal is to develop a comprehensive recommendation system, which has the aptitude to learn the user long and short-term preference for the next POI recommendation and is a considerable attractive research interest. Since users check-in activities are independent and indefinable and can be viewed as long and short term sequence, which equally determine the user’s preference for the next destination. Moreover, the previous methods focuses on the geographical relationship of users among recently visited (POIs) and neglect the user's general interest. To addresses, the issue of (POI)-recommendation, the comprehensive model is given for learning user long and short term preferences. Which considers both recent successive information of users and their general taste simultaneously. The long term module utilizes fusion technique to capture the user's next (POI) preference, by computing the historical visit frequency of users to a particular venue representing their general interest. Whereas the short term preference module utilizes an attention mechanism, to learn the users’ recently visited locations at a specific time and location using spatio temporal based attention model. The given model in this thesis has shown prominent results with an accuracy of 57.7% at N=30 for cold-start-users and 60.7% for Neural network and Random forest respectively. However these results is improved using on non-cold-start users to 79.1% and 77.9% at N=30. Besides the existing methods which neglect the user’s long-term behavior. This work targets to achieve improvement by using fusion model on real-word check-in information and access the model performance in terms of non-cold start and cold-start users which will overcome data sparseness problem in user check-ins, to achieve effective results, and will help in different applications of recommender systemItem Predictionof the user's future location based on past Trajectories(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Umar; SP18-RCS-018Nowadays the use of technology is very common in human life and a large number of people have cell phones, PDAs, or fitness wristbands for their personal use. These modern devices have many powerful applications based on their hardware specifications. GPS hardware module is commonly available in all the above mentioned devices and it generates the GPS log data which are the key points of movement patterns for the individual. It is believed that continuously capturing the user GPS log data and then mining the trajectories patterns can be useful to predict the future location of the user. And it is useful in Smart Advertisement Campaign, Intelligent Transportation System and Smart Reminders, etc. Several studies have been carried out on monitoring the user's location. But there are some deficiencies regarding the individual to collective and even hybrid prediction. However, these studies have not utilized the user's daily routine trajectory patterns for assistance. This work aims to extract the meaningful trajectories patterns from large GPS data of daily routines which may be useful for the prediction of the next possible movement activities of individuals. The dataset which is used in this research is Geolife Trajectories in which 182 users' data captured over three years. There are 17,621 trajectories recorded by mobile phone GPS.In this research,the Hidden Markov Model(HMM) and K Means Clustering are used for the future prediction ofan individual’s movement. The proposedwork is concentrated on the user's past day routine as well as time frame. The model uses these parameters as input and able to give results like “Where is the person physically present when it is a Friday?” or time and day bounded queries like “Where is the person physically present between 5:00 pm to 8:00 pm on Sundays?”.The experiment is conducted over the 182 user’s data and achieve the individual accuracy is upto83% as well as combined accuracy is an average of 35.64% recorded.Item Group Spam identification in Online Product Reviews(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) GHULAM MEHMOOD; SP17-RCS-017; LHR TP 6400; Dr. Hamid Turab MirzaIn this era of e-commerce, user’s opinion about a product on the online review system is of great importance, as it provides guidance for people to decide. Being very important, people used to write fake reviews about the products, called opinion spamming. Detecting opinion spams in online review platforms is a challenging task drawing attention from research communities. It is a persistent campaign between the spammers and platforms. Grouped opinion spamming is the main type of opinion spamming in the online review system these days. For that purpose, usually people make multiple accounts to write fake reviews or they pay to crowdsourcing platforms to write fake reviews for promotion of their product or demotion of their competitor’s product. Group spam reviews are more damaging for online review systems as reviews from many peoples about a product either it is positive, or negative can easily deceive peoples as compared to a single spam review. These spam review groups should be detected so that reviews about that product reflect genuine user opinion. Many researchers try to resolve this problem using behavioral and linguistic features of the users and reviews. Many machine learning models are being adapted to solve this problem but could not resolve this problem completely. The purpose of this research work is to design a framework that detect group spammer who targets online review systems. This framework has used linguistic, behavioral, and structural features to dig out all such spammer groups who write fake reviews. First, constructed a reviewer-product network between reviewers and products. Then written an algorithm to find out collusiveness score between reviewers who have commonly reviewed a product and constructed a network between reviewers. Then all those edges (reviewer pairs) whose score was below a threshold valued was removed from the network. After that extracted high quality candidate spammer groups by using a novel algorithm. Five best group spam indicators are used to calculate spamicity score of candidate spammer groups. The candidate groups whose spamicity score was greater than a threshold values (says 0.6) was considered as spammer groups. For the evaluation of proposed algorithm, experiments performed on 3 labeled datasets from Yelp. The system extracted spammer groups from online reviews with precision of 0.89 @ top 50 spammer groups.