---
title: Unsupervised ML in Financial Time-Series Analysis
url: https://www.ml-quant.com/papers/ssrn/4503933/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4503933
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4503933
featured: 2023-07-12
citations: unknown
topic: Econometrics & Forecasting
---


# Unsupervised ML in Financial Time-Series Analysis

The study merges ontological methodology and temporal clustering to detect structural changes and crucial periods in financial time series, building on prior research in commodity markets.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4503933
- Identifier: SSRN 4503933
- Released: 2023-05-14
- First featured: Quant Letter No. 7 (2023-07-12): https://www.ml-quant.com/issues/2023-07-12/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [Cross-border Commodity Pricing Strategy Optimization via Mixed Neural Network for Time Series Analysis](https://www.ml-quant.com/papers/arxiv/2408.12115/): The paper presents a new method using the hybrid neural network model CNN-BiGRU-SSA for precise prediction and optimization of cross-border commodity pricing strategies, demonstrating superior performance on various datasets.
- [Forecasting Oil Prices with VRP and Google Data](https://www.ml-quant.com/papers/ssrn/4534884/): The paper suggests that incorporating variance risk premium and Google search data into models improves real oil price forecasts, with penalized regressions providing the best results.
- [Forecasting GCC Financial Stress with Neural Networks](https://www.ml-quant.com/papers/repec/kap-apfinm-v-30-y-2023-i-3-d-10-1007-s10690-022-09387-3/): The research uses a One-Dimensional Convolutional Neural Network to predict financial stress in the GCC oil, stock, and bond markets, and finds that financial stress indices and oil significantly improve forecasting performance and risk hedging.
- [Regime Switching in Commodity Prices](https://www.ml-quant.com/papers/repec/taf-apeclt-v-31-y-2024-i-4-p-338-345/): A study from 1959 to 2022 using a 3-state Markov-switching model found that oil prices are more volatile than copper prices, reacting more to market cartelization, war episodes, and global demand shifts.
- [Forecasting Gold Price](https://www.ml-quant.com/papers/repec/spr-annopr-v-334-y-2024-i-1-d-10-1007-s10479-021-04187-w/): The paper suggests using the eXtreme Gradient Boosting (XGBoost) machine learning model and Shapley additive explanations (SHAP) for accurate forecasting and interpretation of gold price fluctuations, surpassing other advanced models.
- [Forecasting the Risk-Free Rates: Practical Forecasting Model for the Future of 10-Year US Treasury Yield through Exogenous Variables](https://www.ml-quant.com/papers/ssrn/4780234/): The study introduces a forecasting model for predicting the 10-Year US Treasury Yield based on variables like exchange rates and crude oil prices.