Analysis of Financial Data to Plan and Forecast for Resource Allocation by Using Double Machine Learning

DOI

10.2991/978-94-6463-866-0_30How to use a DOI?

Keywords

Company Revenues; Data Cleaning; SVM; KNN; Random Forest; Stock prices

Abstract

This research introduces a novel framework titled “Analysis of Financial Data to Plan and Forecast for Resource Allocation Using Double Machine Learning”, which aims to overcome the limitations of traditional forecasting methods in financial analysis. Existing models such as Arima and Long Short Term Memory (LSTM) Network have capacity in time series model, but have performed significant deficiencies. ARIMA is forced into linear, stable data and lacks the ability to model non-lecture patterns. Although LSTM improves prognosis by capturing long term addiction, it requires extensive calculation resources and large datasets, often overfit and reduces gratitude to real time. To solve these challenges, the study suggests a complete-stage approach to use advanced machine learning techniques, including the Support Vector Machine (SVM), K nearest neighbor (KNN), decision trees, linear regression and random forests. These models are capable of handling both linear and non-linear data, which require low prices, and increased scalability and interpretation are offered. Unlike traditional models, the proposed classification and improved methods provide better generalization, strength for noise and the ability to work effectively with high-dimensional and complex datasets. The original double machine in the framework (DML), which distinguishes the estimate for the cause of the cause of the prediction of the result. It reduces bias, improves the interpretation and enables more reliable decisions in planning and resource allocation tasks. Comparative evaluation using real financial data sets shows that proposed functional prediction improves existing models in terms of accuracy, calculation efficiency and adaptability for dynamic market conditions. This research helps to promote financial planning and analysis (FP and A), which integrates one with modern machine learning, providing a more accurate and responsive system for fore- casting and strategic resource management.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Karthik Elangovan
AU  - V. Venkata Poojitha
AU  - J. Dharahasini
AU  - D. S. Kumuda Valli
PY  - 2025
DA  - 2025/10/31
TI  - Analysis of Financial Data to Plan and Forecast for Resource Allocation by Using Double Machine Learning
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 357
EP  - 368
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_30
DO  - 10.2991/978-94-6463-866-0_30
ID  - Elangovan2025
ER  -