---
title: SCFI Forecasting with Deep Learning
url: https://www.ml-quant.com/papers/ssrn/4973768/
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 4973768
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4973768
featured: 2024-10-03
citations: unknown
topic: Econometrics & Forecasting
---


# SCFI Forecasting with Deep Learning

A deep learning model effectively uses Chinese commodity futures prices to predict the Shanghai Containerized Freight Index, according to a study.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4973768
- Identifier: SSRN 4973768
- Released: 2024-09-30
- First featured: Quant Letter No. 68 (2024-10-03): https://www.ml-quant.com/issues/2024-10-03/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [Oil Price Forecasting: Machine Learning vs Deep Learning](https://www.ml-quant.com/papers/repec/spr-annopr-v-345-y-2025-i-2-d-10-1007-s10479-023-05400-8/): Machine Learning vs Deep Learning: The study reveals that deep learning methods, particularly the long short-term memory approach, are more effective than machine learning methods like the support vector machine in predicting oil prices, especially during crises.
- [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.
- [Quantile deep learning models for multi-step ahead time series prediction](https://www.ml-quant.com/papers/arxiv/2411.15674/): The article introduces a new deep learning framework for predicting multi-step time series, which improves the performance of deep learning models. It has been effectively tested on Bitcoin and Ethereum, demonstrating its ability to manage volatility and provide useful information for decision-making.
- [Geometric Deep Learning for Realized Covariance Matrix Forecasting](https://www.ml-quant.com/papers/arxiv/2412.09517/): A new method for forecasting asset return covariance matrices using a Riemannian-geometry-aware deep learning framework outperforms traditional methods by considering the geometric properties of the matrices.
- [Distributional Refinement Network: Distributional Forecasting via Deep Learning](https://www.ml-quant.com/papers/arxiv/2406.00998/): The article introduces the Distributional Refinement Network (DRN), a model that enhances predictive performance and interpretability in actuarial modelling by merging a baseline model with a flexible neural network.
- [A Comparison of Standard Statistical, Machine Learning and Deep Learning Methods in Forecasting the Time Series](https://www.ml-quant.com/papers/ssrn/4840148/): The accuracy of Machine Learning and Deep Learning in forecasting macroeconomic indicators is compared to the traditional statistical method ARIMA.