Browsing by Subject "Random Forest"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Restricted Building a Machine Learning Model to Forecast Consumer Revenge Spending Behavior in the Post COVID-19 Travel Industry(2023) Wing Lam Kong; Artinger, Florian; Villegas, Erick Behar; Faculty of Business Administration; Berlin International University of Applied SciencesAI-GENERATED ABSTRACT: Abstract: This paper aims to build a machine learning model to forecast consumer revenge spending behavior in the post Covid-19 travel industry. Covid-19 has created a new phenomenon "Revenge Spending", where consumers spend excessively in order to compensate for the negative emotion and constraint experienced during the pandemic. This study utilized travel related factors like travel intentions and financial variables to train the machine learning models which included Logistic Regression, Random Forest and Decision Trees. To evaluate which predictive model performs the best in predicting consumer revenge spending behavior in post pandemic travel, cross-validation techniques, accuracy, precision, recall, F1-score, and AUC-ROC metrics were used. The findings of the study bring a meaningful understanding of consumer revenge spending behavior in travel and offer some insight on the key features that are influencing this behavior. Keywords: consumer revenge spending, post Covid-19, travel industry, machine learning, Logistic Regression, Random Forest, Decision Trees, predictive modeling, evaluation metrics, travel behaviorItem Restricted Unsupervised Machine Learning Models for User Segmentation in a Mobile App : Evaluating the Effectiveness(2023) Elena Sidorenko; Artinger, Florian; KoƧ, Hasan; Faculty of Business Administration; Berlin International University of Applied SciencesAI-GENERATED ABSTRACT: Abstract: Context: User segmentation is an effective tool to understand your users' needs and make data-driven decisions. With limited resources many startups have. Would user clustering with unsupervised machine learning models be effective? Objectives: The thesis consists of a literature review, two interviews, and data analysis. It evaluates how effective the different unsupervised models are in application to user segmentation in a mobile application. Methods: a convenience sample interview was conducted with the chief executives of a startup to get an understanding of primary goals and objectives. Data were analyzed with the application of dimension reduction (PCA, t-SNE, UMAP, correlation coefficient, variance threshold), clustering (K-Means, DBSCAN), and supervised models for predictive analysis (Random Forest, Lasso, Logistic Regression). Results: It was possible to identify 4 different clusters of users within the app with unique behavior. Conclusion: The application of PCA, K-Means, and Random Forest was the most effective for a highly dimensional dataset. This user segmentation was valuable, but not new to the chief executives to the company. Meaningful insights were drawn from data analysis. Keywords: user segmentation, unsupervised learning, machine learning, mobile application, PCA, K-Means clustering, Random Forest, data analysis, startups, user behavior clustering