Browsing by Author "Dr. Jawad Shafi"

Now showing 1 - 3 of 3

Multi-label Financial Text Classification: Corpus and Methods
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Laraib Khalid; FA21-RCS-018; LHR TP 8460; Dr. Jawad Shafi
Multi-label financial text classification is evolving but widely researched Natural Language Processing (NLP) task of the current decade. In the recent past, several research efforts have been reported for financial text classification for English and other European languages for instance. Moreover, they are performed for single-label classification (i.e., a document/text is labeled with a single label). However, there is a dearth of South Asian languages, particularly Urdu. Which has around 300 million (non)native speakers around the world and whose digital text is increasing day by day. Unfortunately, very less research efforts have been addressed for Urdu NLP, for instance, financial text classification. Therefore, this research work addresses this research gap for the Urdu language by developing standard evaluation resource and applying baseline supervised and deep learning techniques using multi-label (document/text is labeled with multi labels) classifiers on the proposed corpus. Our proposed Urdu Multi-label Financial Text Classification (UML-FTC-23) corpus contains 24,340 documents and contains different genres and text of business domain. The UML-FTC-23 has been manually annotated with 13 labels ensuring detailed and comprehensive classification of the financial documents/text. It is worth noting that each document in our corpus has been assigned a minimum of two labels and a maximum of nine labels to understand the fine-grained analysis of the financial text and to provide the multi-label classification of text. To demonstrate the quality of the proposed corpus, UML-FTC-23 has been evaluated for multi-label financial text classification by using baseline approaches: 1- Bag of Words (BoW) n-gram, and 2- Term Frequency-Inverse Document Frequency (TF-IDF). Additionally, we have used eight different multi-label classifiers on extracted features. The proposed techniques have been evaluated using several multi-label evaluation measures for instance, exact match, hamming loss, and F1. Furthermore, we have used deep learning methods, including CNN, LSTM, GRU, and RNN on UML-FTC-23 corpus. Result demonstrates that the supervised TF-IDF technique with the multi-label binary relevance classifier achieves the best F1 score of 0.89. Moreover, on the best result using deep learning method are with the CNN which produces the 0.81 F1 score. This indicates that the proposed corpus and techniques are of worth and can be used in various research fields. The proposed corpus and resources are freely available for academic research purposes.
REAL ESTATE PRICE PREDICTION SYSTEM-REPPS
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2022) Muhammad Umais Hassan (SP18-BCS-179), Mubariz Ali Ghauri (SP18-BCS-075), Talha Imtiaz (SP18-BCS-079); LHR TP 8026; Dr. Jawad Shafi
With the increase in number of housing societies and real estate business a large number of computational developments has been carried out globally in this area. Consequently, several real estate prediction systems have been proposed in recent past. However, few research and development attempts have been carried out in this area in Pakistan. Furthermore, these systems can only provide a platform for real-estate prices and there is a dearth for prediction system in Pakistan. This research and development study address this research gap by proposing a real-estate price prediction system in Pakistan and for only big cities. Our research and development contribution in this area will be two-fold: (i) corpus generation and (ii) by applying state-of-the-art machine approaches to predict real estate prices.
Work-Whiz
(Library Information Services, COMSATS University Islamabad, Lahore Campus, 2023) Abdul Rehman (FA20- BSE-073); Adnan Ahmad (FA20- BSE-070); Junaid Mumtaz (FA20- BSE-054); Dr. Jawad Shafi
With the increase of digital online services over the web, the demand for efficient/effective and convenient digital solutions to everyday problem is on increase. Online platforms support so many of our daily activities that we have become dependent on them in our personal and professional lives. We rely on them to buy and sell goods and services, to find information online, and to keep in touch with each other. We use them for entertainment, news, transportation, accommodation, finding jobs and employees, finding apps, and many other purposes. [1] Therefore, as a result several industries has proposed and provided a solution to their services digitally, for instance, ordering food, or sale purchase of products. This problem has been addressed internationally where several IT solutions have been proposed and exist. However, there are very less IT efforts that have been reported and addressed for Pakistan. Pakistan which consists of around 241.49 million [2] population and is increasing rapidly. Providing the physical solution for such an increasing population is a time-consuming, laborious, and thus expansive task. Therefore, this Final Year Project (FYP) proposes and presents the online solution (thereafter Work Whiz) of several services using the web and with the integration of Artificial Intelligence (AI). The primary objective of FYP is to create a comprehensive as well as user-friendly website and mobile application with the integration of AI features to facilitate users. Users will be provided with several services (for instance, plumbing, home repair, car maintenance, etc.), book appointments, request quotations, see reviews, and post tasks including real-time tracking of service providers, notifications, and in-app messaging. Furthermore, service providers can add further services, view detailed profiles of service providers, and read reviews and ratings from previous customers. Moreover, the users will also have the facility to give reviews which our AI-based integrated module automatically analyses and recommends to the users.