Browsing by Author "Dwamena, Harriet Achiaa"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A supervised machine learning algorithm for detecting and predicting fraud in credit card transactions
    (Decision Analytics Journal, 2023-03-06) Afriyie, Jonathan Kwaku; Tawiah, Kassim; Pels, Wilhemina Adoma; Addai-Henne, Sandra; Dwamena, Harriet Achiaa; Owiredu, Emmanuel Odame; Ayeh, Samuel Amening; Eshun, John; 0000-0001-6997-7969
    Fraudsters are now more active in their attacks on credit card transactions than ever before. With the advancement in data science and machine learning, various algorithms have been developed to determine whether a transaction is fraudulent. We study the performance of three different machine learning models: logistic regression, random forest, and decision trees to classify, predict, and detect fraudulent credit card transactions. We compare these models’ performance and show that random forest produces a maximum accuracy of 96% (with an area under the curve value of 98.9%) in predicting and detecting fraudulent credit card transactions. Thus, we recommend random forest as the most appropriate machine learning algorithm for predicting and detecting fraud in credit card transactions. Credit Card holders above 60 years were found to be mostly victims of these fraudulent transactions, with a greater proportion of fraudulent transactions occurring between the hours of 22:00GMT and 4:00GMT.
  • No Thumbnail Available
    Item
    A supervised machine learning algorithm for detecting and predicting fraud in credit card transactions
    (Decision Analytics Journal, 2023-03) Afriyie, Jonathan Kwaku; Tawiah, Kassim; Pels, Wilhemina Adoma; Addai-Henne, Sandra; Dwamena, Harriet Achiaa; Owiredu, Emmanuel Odame; Ayeh, Samuel Amening; John Eshun; https://orcid.org/0000-0001-7881-3069
    Fraudsters are now more active in their attacks on credit card transactions than ever before. With the advancement in data science and machine learning, various algorithms have been developed to determine whether a transaction is fraudulent. We study the performance of three different machine learning models: logistic regression, random forest, and decision trees to classify, predict, and detect fraudulent credit card transactions. We compare these models’ performance and show that random forest produces a maximum accuracy of 96% (with an area under the curve value of 98.9%) in predicting and detecting fraudulent credit card transactions. Thus, we recommend random forest as the most appropriate machine learning algorithm for predicting and detecting fraud in credit card transactions. Credit Card holders above 60 years were found to be mostly victims of these fraudulent transactions, with a greater proportion of fraudulent transactions occurring between the hours of 22:00GMT and 4:00GMT.
  • Thumbnail Image
    Item
    Modelling of grain yield in maize
    (May 12, 2016) Dwamena, Harriet Achiaa
    Grain yield is very important in maize production for breeders at the Crops Research Institute (CRI) of Ghana. However the yields of most varieties that are high yielding released by breeders does not perform so well after some of their release. This study was carried out to nd what causes the reduction in yield of these maize varieties of CRI over the years. An autoregressive moving average model (ARMA) was tted using a 20 year data (1995-2014) from CRI Fumesua. A multiple linear regression model was also tted to study factors a ecting grain yield in maize. Flowering data recorded on a trial eld at Fumesua research station in 2014 was used for the regression model. The study revealed that ARMA (2, 2) was found to be most suitable model for the di erenced series of maize yield. The multiple regression model showed that the factors plants height, days to owering and eld weight were statistically signi cant at 0.05 level. These factors (plants height, the days to ower and eld weight) are signi cant factors a ecting maize grain yield in Ghana.