RT Journal Article
T1 Enhancing financial time series forecasting through topological data analysis
A1 De Jesús, luiz Carlos
A1 Fernández-Navarro, Francisco de Asís
A1 Carbonero-Ruz, Mariano
K1 Análisis de datos
AB Topological data analysis (TDA) is increasingly acknowledged within financial markets for its capacity to managecomplexity and discern nuanced patterns and structures. It has been applied effectively to uncover intricate relationshipsand capture non-linear dependencies inherent in market data. This manuscript presents a groundbreaking study that delvesinto integrating features derived from TDA to improve the performance of forecasting models for univariate time seriesprediction. The research specifically examines whether incorporating features extracted from TDA-such as entropy,amplitude, and the number of points obtained from persistent diagrams can provide valuable supplementary information tothe baseline forecasting model. Thus, the aim is to determine if these TDA-derived features can boost forecasting accuracyby offering additional insights that existing models might overlook. The N-BEATS model serves as the baseline forecasting model due to its robust generalization capabilities and flexibility in incorporating additional features into the model.The proposed methodology is compared against a univariate N-BEATS model without additional features and otherstrategies incorporating supplementary features such as temporal decomposition and time delay embeddings. The evaluation includes forecasting for six cryptocurrencies across four distinct time scenarios and four traditional financialinstruments across two scenarios each, resulting in 32 datasets. The results obtained were promising, as the proposedmethod, N - BEATS +TDA, achieved the best results in mean performance and mean ranking for the three metrics considered(MAPE, MAE, and RMSE). Significant differences were observed with the rest of the proposed methods using a significance level of a α = 0:10, highlighting the effectiveness of integrating TDA features to enhance forecasting models.
PB Springer Nature
YR 2025
FD 2025-01-17
LK https://hdl.handle.net/10630/36603
UL https://hdl.handle.net/10630/36603
LA eng
NO de Jesus, L.C., Fernández-Navarro, F. & Carbonero-Ruz, M. Enhancing financial time series forecasting through topological data analysis. Neural Comput & Applic (2025). https://doi.org/10.1007/s00521-024-10787-x
NO Funding for open access charge: Universidad de Málaga / CBUA
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026