Data Analytics
Permanent URI for this collection
Browse
Recent Submissions
Item Interactive analysis and prediction of us stock prices using time series models in R(Dublin Business School, 2020) Kam, Yean Pyng; Hoare, TerryNo abstract provided.Item Supervised binary image classification using machine learning and convolutional neural networks(Dublin Business School, 2020) Scanlan, Seamus; Kaushik, AbhishekMachine Learning and Deep Learning Algorithms were investigated in terms of their ability to perform a supervised binary image classification task involving the Kaggle Dogs vs Cats dataset. Machine Learning algorithms struggled to achieve above 60% training accuracy. Though the CNNs tended to overfit, the inclusion of regularisation via dropouts reduced this effect and the optimal deep learning algorithm developed using Convolutional Neural Networks achieved a training accuracy of 96% and a validation accuracy using unlabelled images of 94%. In a straight comparison the optimal CNN model had an AUC of 94% compared to 51% for kNN and 58% for Naive Bayes when tested using unseen data.Item Pharmacy cost visualiation and comparison(Dublin Business School, 2020) Tobin-Smith, Sarah; ODonnell, RoryNo abstract provided.Item Using Twitter data to identify public sentiment towards the COVID-19 pandemic in Ireland(Dublin Business School, 2020) Raina, Salil; Hoare, TerryNo abstract provided.Item Anti-money laundering detection and customer segmentation(Dublin Business School, 2020) Kuvaeva, Nadezda; Sharma, ShubhamIn this project we going to cover best practices of the anti-money laundering techniques and methods, such a customer segmentation based on suspicious behaviour and fraud detection machine learning algorithms. The goal of the project is to define what payment instrument used for the money laundering the most, so financial institution can reinforce their fraud detection process for this specific payment method and work closely with the bank provider. We going to implement and compare different machine learning classification and clustering algorithms and find out what method is more accurate and suits better for crime detection problem on the specific financial instrument.