The work aims to classify the occurrence of sexually transmitted disease (STD) in women using dimension reduction and five classification techniques and then compare their results. For dimension reduction, principal component analysis (PCA) and autoencoder techniques are utilised. The data processed by these techniques are used by Bagging K Nearest Neighbours (KNN), Logistic Regression, Support Vector Machines (SVM), Gaussian Mixture Models (GMM), and Extreme Gradient Booster (XGBoost) for classification and their results are compared. Autoencoder + Logistic Regression emerges as the best model with an f1-score of 0.86, precision of 0.87, recall of 0.86, and an accuracy of 0.917. Autoencoder + GMM emerges as the second-best model with the same f1, accuracy, and recall scores as Autoencoder + Logistic Regression but a lower precision of 0.86. Overall the use of autoencoders as a dimensionality reduction technique on the dataset was greatly beneficial whereas the use of PCA was detrimental.