http://dlib.iit.ac.lk/xmlui/handle/123456789/1351 2026-04-15T06:37:42Z 2026-04-15T06:37:42Z Sivaloganathan, Jayanthan http://dlib.iit.ac.lk/xmlui/handle/123456789/1479 2023-01-18T07:11:39Z 2022-01-01T00:00:00Z

Sales Forecasting Models for Paint and Furnishing Products Sivaloganathan, Jayanthan " This project focuses on creating machine learning and deep learning algorithms or models to forecast sales quantity with higher accuracy for the next 12 months. The current forecast process is not as accurate as desirable, which can be seen, first, on the company financial side and, secondly, on a sold unit delivery time, which has a direct impact on the customer experience. An improved forecasting approach would help the sales and operations planning team of the case company to further develop a more accurate production planning and more optimised material stocks in order to cope and overcome the current problem. The main data sources of this project consist of sales data (internal) and national holidays (external). The outcome of this study is an improved 12-month sales forecasting approach, which consists of recommendations for a new forecast process together with specified actions. By implementing the recommended process and actions, the case company would be able to improve its sales forecast accuracy, which will further improve the efficiency of the Sales and Operation Planning Process. "

2022-01-01T00:00:00Z Perera, Chankami http://dlib.iit.ac.lk/xmlui/handle/123456789/1478 2023-01-18T07:08:19Z 2022-01-01T00:00:00Z

Rare event predictive modelling approach to identify potential customers with high intensity to purchase fixed broadband packages in UWV company Perera, Chankami Perera, Chankami (2022) Rare event predictive modelling approach to identify potential customers with high intensity to purchase fixed broadband packages in UWV company . MSc. Dissertation, Informatics Institute of Technology

2022-01-01T00:00:00Z Amuwattage Don, Dulan http://dlib.iit.ac.lk/xmlui/handle/123456789/1477 2023-01-18T07:04:37Z 2022-01-01T00:00:00Z

Predictive Model to Detect Suspicious Transactions to mitigate the money laundering risk in the Non Banking Finance Industry Amuwattage Don, Dulan In this paper, the researchers have studied the money laundering risk in the non-banking finance industry (NBFI) due to high amount of non-compliance incidents reported by the Central Bank of Sri-Lanka (CBSL). This has led to cause threats to the financial system of the country and further companies under the supervision of CBSL are running the reputation risk and worst case will lose the license to operate as a licensed finance entity. Research has sought to address this matter with the objective of developing a predictive model to detect suspicious transactions. As a result, the researchers could detect the variables that influence the suspicious transactions. This research has developed the model using different five algorithms. The study was directed to develop a classification machine learning model. Except for one algorithm, all other algorithms provided an average of 95% accuracy. Random Forest stood out as it reported 100% Recall for the model. Since the model's prime objective is to detect suspicious transaction the model with the best accuracy and recall were selected, therefore Random Forest is the best predictive model that detect suspicious transactions.

2022-01-01T00:00:00Z Perera, Nipuni http://dlib.iit.ac.lk/xmlui/handle/123456789/1476 2023-01-18T07:01:08Z 2022-01-01T00:00:00Z

Detection of Fraud Invoices using Image Classification | Case Study on Healthcare Invoices Perera, Nipuni "The insurance organizations, need to manage invoices, and transactions regarding healthcare insurance, among others. Customers those who are insurance holders need to hand over the invoices to the agents of the insurance company, after that agents need to verify the invoices based on the given details. Most insurance companies are verifying invoices using a manual process. This is a challenge for the organization because needs to assign a specifically trained person to invoice verification This study is mainly focused to introduce machine learning algorithms that can be adapted to an automated invoice process. Before including machine learning models most important phase is the image processing method. This research has four phases. The first phase is collecting invoices data, the second phase is data cleaning and categorizing, the third phase is Image classification model and image processing implementation, and the fourth phase is implementing machine learning models. Invoices image data has been categorized as doctor appointment invoices, pharmacy invoices, and hospital bills. The image processing used multiple techniques to process the images before integrating with the machine learning models. Such as gray scaling, resizing, and data normalization. After pre-processing the images were used cross-validation for the best results. During the cross-validation in the first iteration, the first group of the five groups was assigned as the Test data, and the rest of the four groups were assigned as train data. Then train datasets have been grouped and flattened. As discussed in the above image pre-processing method has been used during this step for each image in both valid and invalid invoice image data. As the final stage implemented the machine learning models and used Random Forest, Decision Tree, KNN, Naïve Bayes, Support Vector Machine, and Artificial Neural Network algorithms to analyze the accuracy and choose the best model for the invoice fraud detecting process. In the analysis phase of the study has been shown Artificial Neural Network has good performance and all the other machine learning models have more 0.5 accuracy rate. Hence this study has indicated that machine learning algorithms can be adapted for the fraud invoice detection process successfully. "

2022-01-01T00:00:00Z