Browsing by Author "Dr. Hamid Turab Mirza"

Now showing 1 - 13 of 13

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 Mirza
Machine 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%.
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 Mirza
The 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 0.95
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 Mirza
Crime 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.
A Study on Diversification of Online Product Reviews
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2020) Abid Ali; FA17-RCS-034; LHR TP 5982; Dr. Hamid Turab Mirza
Recent studies have boosted the e¬commerce industry which has resulted in increased significance of online product reviews. However, this usefulness of product reviews has also attracted the people who try to manipulate overall product perception by generating fake reviews. Another challenge due to boost in e¬commerce is the information overload which is caused by generation of huge reviews data. This study paves a complete pathway by presenting techniques for removal of spam reviews and by proposing a novel algorithm to retrieve a diversified subset of reviews to reduce the burden of information overload. A diversified set of reviews attempts to cover maximum features of the selected product within a limited number of reviews that ultimately leads to reduction in decision time as well as enhances the credibility and reliability for the user. Spam detection techniques were formulated based on deep learning models whereas novel SENTIMENT AND FEATURE ORIENTED DIVERSIFICATION (SeFOD) algorithm was constructed on the features addressed in each review and the sentiments of the review separately. The proposed models showed prominent results and achieved a maximum spam accuracy of 95.78%, 96.38% and 96.18% for LSTM, GRU and CNN models re spectively. The same results were validated on Yelp hotel reviews dataset. Whereas a new measure for calculating the diversity of the reviews set was adopted named as DivScore. The score nearer to 0 means there is no diversity in the set and hence all the retrieved reviews contain similar features. The far this score goes from 0, the more diversity exists in the diversified set. A DivScore of 7.14 was achieved for the selected product from Daraz reviews dataset while 10.88 was the score when a product was diversified from Yelp reviews dataset. This study can be used by e¬commerce industry to maximize their profits as well as is equally relevant for the general users to better choose relevant product for them
Detection and Diversification of Genuine Online Reviews
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-11-20) Mohammad Nabeel Tariq; SP16-BCS-194; Dr. Hamid Turab Mirza; LHR TP 6314
We are grateful to the Almighty ALLAH who provides all the resources of every kind to us so that we make their proper use for the benefit of mankind. May He keep providing us with all the resources, and the guidance to keep helping humanity. We would not have contemplated this road if not for our parents, who instilled within us a love of creative pursuits, science, and language. To our parents, thank you. They have also been the best friends along this journey to encourage us to look forward to being more than just students. We would like to thank our project supervisor Dr. Hamid Turab Mirza for his guidance and encouragement to work hard and smart. We have found him very helpful while discussing the various issues that occurred during our project work. Lastly, many thanks go to the head of the project, Mr. Naveed Hussain who has invested his full effort in guiding us in achieving the goal, without him, this would not have been possible.
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 Mirza
In 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.
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 Mirza
Recommendation 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 system
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 Mirza
Tourist 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.
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 8358
During 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%.
Spotting Spammer using Group Spammer Behaviour Analysis
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-11-20) Kafeel Ahmad Butt; SP16-BCS-187; Dr. Hamid Turab Mirza; LHR TP 6315
Online shopping has become a metamorphic phenomenon in the IT world. Online reviews are considered the best source of customer’s opinion about a product, and an asset for customers, and organizations for making important buying decisions. Unfortunately, in order to increase the number of profits, promotion or even to demote a rival product, deceptive reviews (Spam) mislead prospective customers to buy the best product and organizations in decision making. Works have been proposed on detecting individual spammer reviews. But group review spamming, which includes a group of swindlers working together to post fake online reviews for promoting or demoting a product/s, has become more damaging. More the size of the group more difficult it is to differentiate them as fake reviews. At first, the work uses hints from behavioral data (timestamp, rating) and interpersonal data (network) to construct a suspicious reviewer graph. Then, it breaks the whole suspicious reviewer graph into k-clique clusters, and we consider such k-clique clusters as highly suspicious candidate group spammers. Finally, it ranks candidate groups by group based and individual-based spam indicators. Count Vectorizer and TF-IDF Vectorizer were used for results evaluation. TF-IDF Vectorizer gave the best results we have seen by providing us with the most reliable curve and greater AUC better than any other test cases. Random Forest gave us the best model with TF-IDF Vectorizer using k=7 and Unigram + Bigram + Trigram with Precision, Recall, and AUROC being 1, 1, and 0.74 respectively.
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 Mirza
Increasingly 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 model
University Expert – An Automated University Application Submission and Admission Guidance System
(Library Information Services, COMSATS University Islamabad, Lahore Campus., 2020-11-20) Haris Akhtar; FA16-BCS-281; Dr. Hamid Turab Mirza; LHR TP 6178
Getting admission in a good university/institution or choosing career is one of the challenge students are facing today. After intermediate examination a student goes to many different university websites, creating many admission portals and end up filling all the different application forms. Now he/she has to submit the admission fee by going to every single mentioned bank and remember in all this process he/she is also preparing for the entrance test exams, searching last dates to apply, finding past exams for references, finding ways to calculate aggregate and last year closing merits of different universities. Now what if a student fills a single application form and applies to as many universities he wants without keeping track of everything and get all the resources he/she needs at a single platform. Well that is the concept behind idea of “University Expert”. An Automated platform to make admission process smooth and automated i.e. one stop solution for applying in multiple universities of Pakistan through one single application form along with guidance system, entry test preparation(Expert book), university comparison, counselling sessions, aggregate calculator and weekly informative videos about universities. A module of merit prediction i-e predicating if the student can get admission in a university by comparing it to current students data studying in that institution. Complete guidance for student to choose and apply in best suitable university by going through an expert system. A website (for user interface) and automatic form filling module using python scripts so student has to fill just one form and all the applying process is done through that automation. So far this project has successfully catered 22 clients, sold 75 books, provided services to two major universities, counselled 100+ students and has been incubated at two business incubation canters (Netsol & SSBC Lahore)
User Interest Base Product Ranking Using Opinions’ Aspects
(Library Information Services COMSATS University Islamaabad Lahore Campus, 2020) Ahtsham Shoukat; FA17-RCS-011; LHR TP 6401; Dr. Hamid Turab Mirza
Due to Online shopping trend, a vast number of reviews are generated on daily basis. These reviews help users in selection of products or services. Most of the existing works utilize these reviews in different research areas. Ranking products using these reviews is one of them. Recent studies in the area of research did not focus ranking products on the basis of user specification needs. Previous studies did not focus on ranking products on the basis of user specification. Most of the times the negative polarity of aspects given by users in their reviews is neglected while ranking the products. The main contribution of this study is to take negative polarity of the aspects into consideration, to improve the ranking task. To rank products on the basis of user specification, this research considered both polarities (either positive or negative) of the aspects. In which firstly review is broken down into the sentences to cover the cases in which a review contains multiple senti mentsandvariousaspects. Thereafter aspects are extracted from the reviews of products given in the dataset and polarity of products is calculated on sentence level. Then the polarity is mapped with the aspects extracted from the specific sentence of the review. By using the weightage of the positive and negative polarities products are ranked ac cording to user specification needs. Experimental results show that users now possess the power change the weight of polarities and the resultant ranked list will be according to the user. It means if a user doesnotintendtoincludeaspecificpolarity, hemayignorethesamebeassigningweight 0 to that. This study helps users in selection of good products or services. The instant work is performed for English language reviews. This research opens a gate to the natives of different countries to enhance the work for their native languages