Browsing by Author "Rupasinghe, T.D."

Now showing 1 - 5 of 5

Applicability of unsupervised learning algorithms for setting profiles for consumer buying behavior
(Faculty of Science, University of Kelaniya, Sri Lanka, 2016) Paranavithana, I.R.; Rupasinghe, T.D.
The Consumer Buying Behaviour consists of a summation of attitudes, preferences, intentions and, decisions taken by them. The process that customer buys a product or service varies for each individual and each category of products they may purchase. With the development of Information Technology, the products and the behaviour of purchasing those products have drastically changed and become more unique to individuals. With respect to these changes, the data collection and analysis have become more dynamic and customer data has become larger and nosier in terms of volume and complexity. As a result of that, handling, analysing, and interpreting customer Point of Sale (POS) data has become a challenge for Retail Supply Chains (RSC) who wish to segregate customers into specific niche markets. Furthermore, it makes increasingly difficult for the retailer to find out when a person comes and buys the products from their outlets and to predict his/her behaviour for the subsequent purchases. As a solution for the aforementioned problems faced by the retailers, a novel a consumer buying behaviour profile mechanism is proposed. The profiles are created with respect to the frequency, time-stamp, and product category using a large POS dataset. The Unsupervised learning techniques were utilized in categorizing consumers in determining similar purchasing behaviour using K-means, Expectation Maximization, and Hierarchical Agglomerative Clustering (HAC). Along with the above clustering techniques, text mining techniques were used in categorizing the product descriptions to create the desired product categories. The study has used data from the UCI machine learning repository with 541,909 POS type records and has applied the aforementioned unsupervised learning techniques to setup the profiles. It has unveiled product related and non-product related charateristics for the given POS data and has laid a novel foundation to construct the profiles to determine buying behaviour. Furthermore, these profiles can be used in segmentation of consumers, RSC specific promotions, and to predict future possibilities to minimize inventory related problems.
An assessment of machine learning-based training tools to assist Dyslexic patients
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Sathsara, G.W.C.; Rupasinghe, T.D.; Sumanasena, S.P.
Dyslexia is a language based disability, where the patients often have difficulties with reading, spelling, writing and pronouncing words. The reading speed of Dyslexics tend to be lower than their equivalents, because of slow letter and word processing. Inspite of this disorder, a dyslexic person can be trained to read in normal speed. There are manual methods and some technical improvements can be reported such as the live-scribe smart pen, Dragon Naturally Speaking, Word processors, and Video Games. This study provides an assessment about the Machine Learning (ML) based techniques used for Dyslexic patients via a systematic review of literature, and a proposed ML based algorithm that will lay foundation for future research in the areas of machine learning, augmented and healthcare training devices.
Cluster-based Transportation Optimization – A Case Study from Pharmaceutical Supply Chains (PSC).
(In: Proceedings of the International Postgraduate Research Conference 2017 (IPRC – 2017), Faculty of Graduate Studies, University of Kelaniya, Sri Lanka., 2017) Niwunhella, D. H. H.; Rupasinghe, T.D.
Transportation planning attempts to allocate fixed logistics capacity in the best possible way, for particular business requirements. This study focuses on the pharmaceutical supply chains, as optimization of medicine distribution routes has become an urgent issue that needs to be solved. The cost components of many distribution and transportation systems represent the routing and scheduling of vehicles, but there are only a few optimization approaches that have been introduced to effectively solve Vehicle Routing Problem (VRP). Therefore, this study presents a simulation based solution approach for transportation optimization, in order to minimize the cost, based on the pre-identified pharmaceutical product clusters. The simulation models are developed using the SupplyChainGuru® modelling and simulation platform, where vehicle routing models are developed to simulate the inherent features of the product families using test cases from the literature and the benchmark instances listed on the repository of CVRPLib. The study proposes and models five product characteristic-based clusters namely, time sensitive pharmaceuticals, hazardous pharmaceuticals, hybrid pharmaceuticals, condition constrained pharmaceuticals (conditions such as pressure/temperature, etc.), and general pharmaceuticals. The baseline VRP model is compared with the cluster specific VRP models developed for each product cluster. The results of the study depict that the total transportation cost minimizes as the products are routed with respect to the inherent product clusters, than the cost of routing without considering cluster-specific characteristics. The maximum percentage cost reduction is for the general/condition constrained cluster (64.04%), whereas the minimum is for the time sensitive product cluster (0.59%). This product clustering approach of transportation optimization could be utilized dynamically to provide efficient delivery of products to the consumers, and could be adopted in related industrial supply chains.
Determinants of successful implementation of Green Supply Chain Management: From literature review perspective
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Thushanthani, T.; Rupasinghe, T.D.
The purpose of this study is to identify the Green Supply Chain Management (GSCM) best practices and explore the factors influencing the succesful adoption of green supply chain management practices. The authors have used a systematic review of literature approach to collate 27 articles ranging from automobile, beverages, construction, electrical, hospitality, power generating and, general industries. The findings are revealed under five categories namely; green procurement, green design, green packaging, green operations, green manufacturing and reverse logistics incorporating 48 critical success factors under five themes, namely; Organizational Commitment (OC), Knowledge Base (K), Operational Dynamics (OD) , Market Pressure (MP) and Exogenous (E).
Predictive analytics for decision making: Human computer interaction perspective from online purchasing
(Faculty of Science, University of Kelaniya, Sri Lanka, 2016) Kiringoda, N.M.; Rupasinghe, T.D.
The internet-based technologies have influenced all parts of human lives within a short time. The internet is used for conducting commercial transactions electronically and it is the base of the concept called e-commerce. Most of the businesses have engaged in utilizing the Internet to sell their product and services. Hence, spend millions of dollars to create and maintain their corporate websites. The consumer behaviour in online shopping is continuously changing due to the personal characteristics of the shoppers as well as the environmental factors. The e-commerce based transactions are becoming increasingly popular and the number of consumers who interact with the e-commerce sites have been drastically increased along with the reviews they leave after purchases. This makes it difficult for potential customers to read, comprehend, and make sound decisions on individual purchases. Furthermore, makes even difficult task for the corporate entities to track their websites to manage customer opinions. Text mining is the process which explores, evaluates, and interprets data patterns by converting unstructured text data into more meaningful information. In this study, we address the aforementioned issues by proposing a Human Computer Interaction (HCI) enabled Naïve Bayes classification approach to categorize the online reviews of e-commerce websites. HCI factors such as; usability, simplicity, and accessibility are considered along with consumer reviews extracted from the attribute dictionaries such as stanford parser. The study has derived different data patterns from the text mining exercises which will be beneficial for predictive analytics from the customers’ as well as from the corporate standpoint for online purchases.