E.C. IGODAN

The growing sophistication of phishing attacks continues to threaten digital security, causing financial losses, data compromise, and reduced trust in online platforms. Traditional blacklist and rule-based systems struggle to detect newly emerging phishing patterns, highlighting the need for adaptive, intelligent, and automated approaches. This study addresses this challenge by developing a machine learning-driven phishing vulnerability prediction model capable of accurately distinguishing phishing websites from legitimate ones. The objectives include dataset acquisition, feature preprocessing, model development, and performance evaluation. A labelled URL-based phishing dataset sourced from Kaggle was cleaned, encoded, normalized, and split using an 80:20 train-test ratio. Four supervised learning algorithms: Logistic Regression, Decision Tree, Random Forest, and Extreme Gradient Boosting (XGBoost), were implemented and assessed using Accuracy, Precision, Recall, and F1-score. Among all models, XGBoost achieved the best performance with an Accuracy of 0.96, Precision of 0.97, Recall of 0.96, and an F1-score of 0.96, demonstrating strong predictive ability and robustness. Random Forest also performed well but with slightly lower scores. The final XGBoost model was deployed in a Flask-based web application to provide realtime phishing detection and user awareness. The findings confirm that machine learning, particularly ensemble-based methods, provides a scalable and highly effective approach to phishing vulnerability prediction. However, limitations include reliance on static URL features, dataset-specific bias, and the absence of behavioural or real-time network indicators. Future work should incorporate hybrid features, adversarial robustness testing, and explainable AI techniques to improve transparency and adaptability to evolving phishing attacks.

The process of estimating property prices in Nigeria remains largely manual, subjective, and
inconsistent, as real estate valuation often depends on personal experience, incomplete records,
or unstructured web data. These limitations create inaccuracies that affect buyers, sellers,
investors, and policymakers. To address these challenges, this study aims to develop a more
reliable and data-driven method for house price prediction using machine learning techniques.
The objectives include collecting and preprocessing a multi-state Nigerian dataset, engineering
relevant features, developing multiple predictive models, and evaluating their performance to
identify the most accurate approach.
A dataset consisting of 28,915 property records scraped from PropertyPro was cleaned,
normalized, and transformed through techniques such as one-hot encoding and Mutual
Information Regression. Four machine learning models, which are Linear Regression, Decision
Tree, Random Forest, and XGBoost, were implemented and evaluated using MAE, MSE, and R².
Quantitatively, the models achieved R² scores of 0.475 (Linear Regression), 0.433 (Decision
Tree), 0.517 (XGBoost), and 0.520 (Random Forest). Qualitatively, Random Forest
demonstrated superior ability to capture nonlinear patterns, handle noisy data, and generalize
across diverse property locations. The best-performing model was deployed through a Streamlit
web application to enable real-time house price prediction for end users.
Despite its success, the study is limited by the absence of macroeconomic variables such as
inflation and interest rates, which play a substantial role in housing market dynamics.
Additionally, challenges in obtaining comprehensive and well-structured real estate data across
all Nigerian states constrained the breadth of the analysis. Future research should integrate
geospatial and macroeconomic datasets to further enhance prediction accuracy and model
robustness.

Malaria remains a global health crisis, particularly in low-resource regions, where traditional diagnostic methods face challenges such as human error, resource constraints, and delayed detection. This project addresses these limitations by leveraging supervised machine learning (ML) to enhance malaria diagnosis and outbreak prediction. The motivation stems from the urgent need for scalable, accurate, and cost-effective solutions to reduce the disease’s burden, which claims over 600,000 lives annually. The objective is to develop robust ML models capable of automating malaria diagnosis using blood smear images and patient metadata while improving outbreak forecasting through environmental and epidemiological data analysis. Methodologically, the study employs supervised learning algorithms, including convolutional neural networks (CNNs) for imagebased detection and random forests for tabular data. Datasets were preprocessed to handle class imbalance and missing values, followed by hyperparameter tuning and cross-validation to optimize performance. Results demonstrated that CNNs achieved 96% accuracy in classifying infected blood cells, outperforming traditional methods like microscopy. Random Forest models yielded 92% recall and 89% precision in predicting malaria risk from clinical data, highlighting their utility in early diagnosis. Additionally, stratified k-fold cross-validation ensured model generalizability across diverse datasets. This work underscores the transformative potential of supervised ML in malaria control, offering tools that enhance diagnostic speed, accuracy, and accessibility. By bridging technological innovation with public health needs, the project contributes to global efforts toward malaria eradication, particularly in endemic regions

Malaria remains a global health crisis, particularly in low-resource regions, where traditional diagnostic methods face challenges such as human error, resource constraints, and delayed detection. This project addresses these limitations by leveraging supervised machine learning (ML) to enhance malaria diagnosis and outbreak prediction. The motivation stems from the urgent need for scalable, accurate, and cost-effective solutions to reduce the disease’s burden, which claims over 600,000 lives annually. The objective is to develop robust ML models capable of automating malaria diagnosis using blood smear images and patient metadata while improving outbreak forecasting through environmental and epidemiological data analysis. Methodologically, the study employs supervised learning algorithms, including convolutional neural networks (CNNs) for image- based detection and random forests for tabular data. Datasets were preprocessed to handle class imbalance and missing values, followed by hyperparameter tuning and cross-validation to optimize performance. Results demonstrated that CNNs achieved 96% accuracy in classifying infected blood cells, outperforming traditional methods like microscopy. Random Forest models yielded 92% recall and 89% precision in predicting malaria risk from clinical data, highlighting their utility in early diagnosis. Additionally, stratified k-fold cross-validation ensured model generalizability across diverse datasets. This work underscores the transformative potential of supervised ML in malaria control, offering tools that enhance diagnostic speed, accuracy, and accessibility. By bridging technological innovation with public health needs, the project contributes to global efforts toward malaria eradication, particularly in endemic regions

The exponential rise in digital banking transactions has heightened the risk of fraudulent and anomalous bank transfers, necessitating intelligent and automated mechanisms for its detection. Traditional rule-based systems often fail to capture evolving fraud patterns, motivating the adoption of machine learning-based anomaly detection techniques. This study aims to develop and evaluate robust unsupervised learning models for detecting anomalies in bank transaction datasets. Specifically, the research applies three state-of-the-art algorithms; Isolation Forest, Local Outlier Factor (LOF), and One-Class Support Vector Machine (OCSVM) to identify irregular transaction behaviors indicative of potential fraud. The methodology involves comprehensive data preprocessing, scaling, encoding, and feature selection to improve model learning. Real-world bank transfer datasets from kaggle were utilized, for this training. Each model’s performance was assessed using standard evaluation metrics, including; Silhouette Score, Anomaly Ratio, and Average Decision Score. Results show that OCSVM performed best (Silhouette = 0.635, strong decision scores), reliably flagging about 5% of records as anomalies. Analysis of flagged transactions revealed consistent patterns high transaction amounts or balance-change ratios, very short or very long intervals between transactions, and activity at unusual hours making the alerts interpretable and practically useful.