http://hdl.handle.net/123456789/132 Sat, 04 Apr 2026 10:51:25 GMT 2026-04-04T10:51:25Z http://hdl.handle.net/123456789/20585 Automated Credit Scoring 03-134221-031, Muhammad Wahaaj Tauqir Commercial clients (business owners, retailers) of wholesale distributors often rely on credit lines to purchase goods, especially during economic crises when banks hesitate to lend to retailers. This affects the sales of distributors, prompting them to offer products on credit. However, when distributors extend credit, they face the risk of customer default. They need a reliable method to evaluate the creditworthiness of their customers to minimize financial loss. To address these challenges, we propose an automated AI driven credit scoring system that automates the evaluation process by analysing several features including customer purchase behaviour, transaction history, and repayment patterns to the interpretable scorecard. The system integrates generative AI–powered variable classification, automated preprocessing, Auto-Monotonic Fine Binning, and advanced ensemble modeling and instant generation of points-based scorecard. Deploying the solution as a secure cloud-native application ensures rapid, accurate, and fully auditable credit decisions significantly improving risk management and operational efficiency for wholesale distributors. Dr. Muhammad Saqib Sohail Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/20585 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/20586 DineSmart: Al Powered Chatbot 03-134221-012, Haider Naeem DineSmart shifts traditional food ordering system to smart chatbot based ordering system. It combines intelligent ordering platform which understands customer intents, extract entities properly, manages complex orders and restaurant operations with robust backend built on powerful Flask-Python backend with flutter used for interactive and user-friendly frontend. This system also integrates multiple technologies including Google’s Gemini 2.5 Flash LLM for conversational AI, Stripe for dummy payment processing, MongoDB for data storage and retrieval and Google Maps API for precise food delivery. Our platform provides dual purpose architecture: providing customers with new ordering experience with giving restaurant administration real time order management, inventory control and business analytics. By doing so DineSmart sets new market standards in the field on food industry. Dr Muhammad Saqib Sohail Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/20586 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/20611 Wuqla AI 03-134221-018, Muhammad Ahsan Wuqla AI is a smart online platform created to enhance the process of accessing information regarding the property-related legal matters in Pakistan via incorporation of Chat bot. The system enables to simplify otherwise complicated legal notions like the ownership issues, inheritance question, and the process of the property transfer to make them more comprehensible and accessible to the broad audience. It offers a well-organized space where one can seek automated legal advice, find legal practitioners, launch live interaction and manage his profile effectively using just one platform. Some of the essential features of the system are AI-based legal query processing, search through lawyers by name, intelligent lawyer recommendation to suit the specific legal issue, chatting consultation, request chat, and feedback and rating system to evaluate the service. All these characteristics contribute to the convenience of users, convenience in decision-making, as they enable communication of the user with the right legal specialist and legal information that can be trusted, in an efficient way. Ms. Summaira Nosheen Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/20611 2026-01-01T00:00:00Z http://hdl.handle.net/123456789/20612 SkinCare:An AI Guide To Skin Wellness 03-134221-036, Subaktgeen Haider Skin diseases represent a significant health concern at a worldwide level, especially in areas where accessibility to dermatologists is restricted, the cost of consulting with them is high and there is a delay in seeking medical attention, which in most instances causes late diagnoses and avoidable complications. Due to the swift growth of smartphones and artificial intelligence (AI), increased interest in high-speed, reliable, and privacy-oriented tools exists that can be used to initiate early awareness of skin-health. The proposed project presents the SkinCare: An AI Guide to Skin Wellness, a mobile app that will analyze skin-condition images in real-time using a quantized TensorFlow Lite model and provides intelligent guidance to users by training a lightweight conversational assistant named Gemini Flash-Lite Pro that will assist users in taking high-quality images, interpreting AI outputs, and offering them safe educational advice. All processing is done on the device to guarantee high privacy and low latency with an average of 0.8 seconds inference time on mid-range Android machines. The HAM10000, ISIC Archive, and Fitzpatrick17k datasets were used to train the AI model, with the preprocessing techniques of normalization, augmentation, and class balancing to make the AI model more robust in different skin tones and under various lighting conditions. EfficientNet-Lite and Optimized MobileNetV3 architectures recorded a competitive accuracy of 8790 percent with a much smaller model size to deploy efficiently on mobile devices. To simulate the actual reality of usage, the development and testing was done in Visual Studio Code upon physical Android devices. Feedbacks on the system were reported to be very satisfying by pilots in terms of the clarity, responsiveness, and user-friendliness. In general, the app confirms the efficiency of integrating edge detection with chatbots into a fast, convenient and privacy-aware solution that can raise skin-health awareness in the early stages and increase the availability of preliminary dermatological consultation, particularly, in communities with lower resources and limited access to them. Ms. Rabia Masood Thu, 01 Jan 2026 00:00:00 GMT http://hdl.handle.net/123456789/20612 2026-01-01T00:00:00Z