arbiter
JournalsPricingAccount

Forecasts of share prices for China with machine learning

Bingzi Jin & Xiaojie Xu

International Journal of Financial Engineering2025https://doi.org/10.1142/s2424786325500227article
ABDC C
Weight
0.48

What the paper says

Forecasts of share prices for the stock market in China represent an important and challenging task for policy makers and investors. In this work, we examine monthly share prices from January 1999 to May 2024 using Gaussian process regressions with a variety of kernels and basis functions. The training of models and the execution of forecasting exercises with estimated models are accomplished via the utilization of cross-validation and Bayesian optimizations. Over the period of time from May 2019 to May 2024, the models that were constructed were able to provide rather accurate projections about the share prices. Specifically, this particular set of models has a relative root mean square error of 3.4761%. It is feasible that our findings may be used either on their own or in combination with other projections in order to create assumptions about movements in share prices and carry out more policy research.

5 citations

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1142/s2424786325500227

Or copy a formatted citation

@article{bingzi2025,
  title        = {{Forecasts of share prices for China with machine learning}},
  author       = {Bingzi Jin & Xiaojie Xu},
  journal      = {International Journal of Financial Engineering},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.1142/s2424786325500227},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Forecasts of share prices for China with machine learning

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.48

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.41 × 0.4 = 0.16
M · momentum0.63 × 0.15 = 0.09
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.