Προβλεπτική αναλυτική με τη χρήση data mining αλγορίθμων
View/
Keywords
Data mining ; Προβλεπτική αναλυτική ; Δεδομένα ; Προεπεξεργασία ; Μοντέλο ; Python ; Μάθηση με επίβλεψη ; Μάθηση χωρίς επίβλεψηAbstract
In today's data-driven world, the ability to predict future trends and behaviors based on historical data is crucial for strategic decision-making across various sectors. This thesis explores the realm of predictive analytics through the application of data mining algorithms, aiming to develop robust models that can forecast outcomes with high accuracy. The research delves into a comparative analysis of several unsupervised and supervised data mining techniques, including clustering, classification, regression, and anomaly detection. Key algorithms such as decision trees, random forests and support vector machines are evaluated based on their performance in different predictive tasks.
The study employs a comprehensive data preprocessing pipeline to handle missing values, outliers, and normalization, ensuring the quality and integrity of the input data. There are used two datasets to validate the effectiveness of the proposed models. The results demonstrate the performance of ensemble methods and deep learning algorithms in capturing complex patterns and making precise predictions.
Moreover, this thesis addresses the challenges of model interpretability and scalability, providing insights into the practical implementation of predictive analytics in real-world scenarios.
Postgraduate Studies Programme
Πληροφοριακά Συστήματα και ΥπηρεσίεςDepartment
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών ΣυστημάτωνNumber of pages
69Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα