Optimizing SAP Predictive Analytics with Automated Hyperparameter Tuning Using Differentiable Optimization

DOI

10.2991/978-94-6463-872-1_36How to use a DOI?

Keywords

SAP Predictive Analytics; Hyperparameter Tuning; Differentiable Optimization; Data-Enabled Predictive Control (DeePC); Backpropagation; Automated Model Optimization; Demand Forecasting; Supply Chain Optimization; Financial Risk Assessment; SAP S/4HANA; SAP Business Technology Platform (BTP)

Abstract

As enterprises increasingly rely on SAP Predictive Analytics for forecasting, anomaly detection, and operational decision-making, optimizing model performance remains a critical challenge. Traditional methods for hyperparameter tuning in SAP AI Core and SAP HANA Predictive Analytics Library (PAL) involve manual tuning or open-loop optimization, both of which can lead to inefficiencies, suboptimal performance, or increased computational costs. To address this, I introduce SAP-PHT (SAP Predictive Hyperparameter Tuning), an automated hyperparameter optimization framework based on differentiable optimization and backpropagation techniques. SAP-PHT leverages data-driven predictive control (DeePC) methods to optimize model parameters dynamically, ensuring robust closed-loop performance without manual intervention. By integrating iterative learning strategies and adaptive parameter tuning, SAP-PHT enhances model accuracy, stability, and resilience against data variations. Experimental evaluations within SAP S/4HANA and SAP Business Technology Platform (BTP) demonstrate significant improvements in predictive model performance, reducing errors in demand forecasting, supply chain optimization, and financial risk assessments. The results highlight the potential of SAP-PHT in stream- lining SAP AI-based analytics, improving business decision-making, and reducing operational costs.

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  - Ashwini Chandrakumara
PY  - 2025
DA  - 2025/11/04
TI  - Optimizing SAP Predictive Analytics with Automated Hyperparameter Tuning Using Differentiable Optimization
BT  - Proceedings of the 2nd International Conference on Sustainable Business Practices and Innovative Models (ICSBPIM-2025)
PB  - Atlantis Press
SP  - 564
EP  - 574
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-872-1_36
DO  - 10.2991/978-94-6463-872-1_36
ID  - Chandrakumara2025
ER  -