Mining big annual statement datasets to predict highly lucrative companies using classification trees and forests

Inhaltsverzeichnis (Table of Contents)

• INTRODUCTION AND PROBLEM DESCRIPTION.
• INTENTION OF THIS THESIS
• PROCEEDING
• INTRODUCTION TO KEY FIGURE ANALYSIS
• THE PRINCIPLE OF KEY FIGURES
• THE CLASSICAL KEY FIGURE ANALYSIS APPROACH...
• MODERN KEY FIGURE ANALYSIS APPROACHES
• LIMITATIONS OF ANNUAL REPORT ANALYSIS....
• THE AVAILABLE DATASET.
• DESCRIPTION OF THE DATASET.
• DATA CLEAN-UP.
• KEY FIGURE SELECTION.
• SIGNIFICANT KEY FIGURE REQUIREMENTS.
• THE SELECTED KEY FIGURES OF THIS ANALYSIS
• Selected class variable
• Selected qualitative key figures..
• Selected absolute key figures..
• Selected relative key figures..
• CLASS ANALYSIS.....
• CLASSIFICATION TREES AND FORESTS.
• PRECONSIDERATIONS
• CLASSIFICATION TREES
• A simple example.......
• Generation of classification trees...
• Pruning an existing tree.
• Relevant properties of CART trees.
• RANDOM FOREST.
• Classification process of a random forest.
• Generation of random forest.
• Relevant properties of random forests
• CLASSIFICATION RESULTS..
• CLASSIFICATION TREE RESULTS......
• Examination of the most precise tree.
• Key indicator importance ranking
• Transfer to data from 2011
• CLASSIFICATION FOREST RESULTS..
• Transfer to data from 2011
• Key indicator importance ranking
• CONCLUSION
• CRITICAL ASSESSMENT.
• OUTLOOK

Zielsetzung und Themenschwerpunkte (Objectives and Key Themes)

This thesis explores the potential of employing classification trees and forests to predict highly lucrative companies based on annual statement datasets. The main goal is to develop a reliable model that can identify financially successful companies by analyzing key figures derived from their annual reports. The study focuses on the identification of significant key figures, their analysis, and the implementation of these findings in the development of classification algorithms.

• Identifying key figures that strongly influence a company's profitability.
• Analyzing the effectiveness of classification trees and forests for predicting company success.
• Evaluating the performance of the developed models on real-world datasets.
• Exploring the applicability of the findings to data from different time periods.
• Assessing the potential limitations and opportunities for improvement of the proposed approach.

Zusammenfassung der Kapitel (Chapter Summaries)

The introductory chapter lays out the thesis's intention, which is to develop a model capable of predicting highly lucrative companies using classification trees and forests based on data extracted from annual statements. The chapter also discusses the procedural steps involved in the analysis.

Chapter 2 provides a comprehensive overview of key figure analysis, covering its principles, classical and modern approaches, and inherent limitations. The chapter delves into the significance of key figures in understanding a company's financial health and provides a framework for selecting and analyzing relevant figures.

Chapter 3 describes the dataset used in the study, outlining its structure and content. It also details the data cleaning processes undertaken to ensure the accuracy and reliability of the data for analysis.

Chapter 4 dives into the selection of key figures for the study, focusing on criteria for determining their significance. The chapter lists the selected key figures, categorizing them into classes based on their nature (qualitative, absolute, and relative). The chapter concludes with an analysis of the class variable, which represents the target variable for classification.

Chapter 5 introduces the classification algorithms used in the study, namely classification trees and forests. It explains the principles behind these algorithms, their generation process, and their relevant properties. This chapter provides a theoretical foundation for understanding how these algorithms operate and are applied in the analysis.

Chapter 6 presents the results of the classification process, focusing on the performance of both classification trees and forests in predicting company success. It examines the most precise tree and provides a ranking of key indicators in terms of their importance in determining classification outcomes. The chapter also explores the applicability of the model to data from a different time period (2011) and assesses its accuracy in predicting financial success.

Schlüsselwörter (Keywords)

The key focus of this thesis is on the use of classification trees and forests for predicting highly lucrative companies based on annual statement datasets. The study analyzes key figures, explores data cleaning techniques, and examines the effectiveness of these algorithms in determining financial success. The thesis focuses on the interplay of data analysis, machine learning techniques, and financial performance evaluation in the context of corporate financial reporting. Key terms include: classification trees, random forests, key figure analysis, annual statements, financial reporting, prediction models, and company profitability.