This research paper is an econometric analysis that investigates the factors influencing household financial satisfaction across European countries using data from the European Social Survey Round 9 (2018/19). The study employs ordered logistic regression methodology to examine how various demographic, socioeconomic, and attitudinal variables predict levels of financial well-being.

This project utilizes association rule mining techniques to analyze an online retail dataset sourced from Kaggle. The goal is to uncover hidden relationships between products that are frequently purchased together, providing actionable insights for optimizing product bundling, targeted marketing strategies, and inventory management. By exploring frequent itemsets and association rules, the analysis offers recommendations that can help businesses enhance their sales performance and improve customer satisfaction through personalized offerings and promotions. Let me know if you need further edits!

In this project, Principal Component Analysis (PCA) is applied to a housing dataset to explore the relationships between various housing features and prices. The analysis begins with a detailed data cleaning and exploratory data analysis (EDA) phase, followed by the application of PCA to reduce the dataset's dimensionality. Using statistical tests like Bartlett's test and the Kaiser-Meyer-Olkin (KMO) test, we evaluate the dataset's suitability for PCA. The results highlight the contributions of key variables and principal components, offering actionable insights while simplifying the dataset for further analysis. This project serves as a practical example of using PCA to handle high-dimensional data in the real estate sector, helping to streamline analysis and improve interpretability without sacrificing essential information.

This analysis explores the clustering behavior of clubgoers based on various preferences, entry times, and demographic information. Using unsupervised learning techniques, we compare the performance of K-Means and DBSCAN clustering algorithms. The optimal number of clusters is determined using the elbow method, and the clustering results are visualized using PCA (Principal Component Analysis) to reveal distinct patterns within the data. DBSCAN's ability to detect irregular clusters and noise is compared with K-Means' performance on well-separated clusters. This study highlights the strengths and limitations of both algorithms in identifying meaningful segments among clubgoers.