Paper: arXiv 2310.16855
Authors: Ryan Chipwanya
Abstract
The stock market has been established since the 13th century, but in the current epoch of time, it is substantially more practicable to anticipate the stock market than it was at any other point in time due to the tools and data that are available for both traditional and algorithmic trading. There are many different machine learning models that can do time-series forecasting in the context of machine learning. These models can be used to anticipate the future prices of assets and/or the directional bias of assets. In this study, we examine and contrast the effectiveness of three different machine learning algorithms, namely, logistic regression, decision tree, and random forest to forecast the movement of the assets traded on the Japanese stock market. In addition, the models are compared to a feed forward deep neural network, and it is found that all of the models consistently reach above 50% in directional bias forecasting for the stock market. The results of our study contribute to a better understanding of the complexity involved in stock market forecasting and give insight on the possible role that machine learning could play in this context.
Complexity vs Empirical Score
- Math Complexity: 4.0/10
- Empirical Rigor: 3.0/10
- Quadrant: Philosophers — conceptual discussion, lower math and empirical scores
Why this score: The paper employs standard ML classifiers (logistic regression, decision trees, random forest) with a basic binary classification task, resulting in low mathematical complexity. The empirical rigor is low because the backtest is limited to a single stock (Sony) with a simple data split, lacks risk/transaction cost analysis, and does not use walk-forward or cross-validation to address time-series leakage.
Research Flowchart
flowchart TD A["Research Goal: Compare ML algorithms for stock market directional bias prediction"] --> B["Data Input: Japanese Equities<br>Time-Series Data"] B --> C["Methodology: Model Training & Evaluation<br>Logistic Regression | Decision Tree | Random Forest | DNN"] C --> D["Computational Process: Time-Series Forecasting<br>Predicting Up/Down Directional Bias"] D --> E["Outcome: Models consistently achieve >50% accuracy"] E --> F["Key Findings:<br>1. ML models feasible for stock market prediction<br>2. Japanese market shows predictable patterns<br>3. All algorithms outperform baseline"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes to evaluate and compare logistic regression, decision tree, random forest, and a feed‑forward deep neural network for forecasting directional bias of assets on the Japanese stock market.
Source sentence
we examine and contrast the effectiveness of three different machine learning algorithms—namely, logistic regression, decision tree, and random forest—to forecast the movement of the assets traded on the Japanese stock market. In addition, the models are compared to a feed forward deep neural network, and it is found t
Assumes 1
- The target variable is a binary indicator (1 for increase, 0 for decrease) of next‑day price movement. data
Source sentence
The “Target” column is used to classify whether the movement will be an increase or a decrease, shown by the numbers 1 and 0 accordingly.
Data
- Kaggle JPX Tokyo Stock Exchange Prediction Competition market-prices public
Source sentence
The Kaggle JPX Tokyo Stock Exchange Prediction Competition, which was organised by the Japanese Exchange Group [8] will serve as the data set that we will be utilising in this study.
Costs
Unclear - sources disagree
Source sentence (the authors' words)
However, it is essential to recognise the limitations of our study, specifically the lack of advanced metrics and trading performance data.
Finds 5
- Logistic regression achieved 55% accuracy in directional bias prediction. predictive-accuracy
Source sentence
Our LR model scored a remarkable accuracy of 55%, which indicates that it is able to accurately estimate directional trends in slightly more than half of the situations.
- Decision tree achieved 59% accuracy, outperforming logistic regression. predictive-accuracy
Source sentence
The LR model was surpassed by the baseline DT model, which had an accuracy rate of 59%.
- Random forest achieved the highest accuracy of 63%, demonstrating the benefit of ensemble methods. predictive-accuracy
Source sentence
the high-performing RF classifier had an accuracy of 63%, demonstrating the benefits of using ensemble methods to improve prediction accuracy.
- The feed‑forward neural network obtained a test accuracy of roughly 59% and an F1 score of 0.74. predictive-accuracy
Source sentence
the results showed that the model had a test loss of roughly 0.68 and a test accuracy of 59%. The F1 score, which exhibited a balanced performance with a score of 0.74
- All models consistently reached above 50% directional bias forecasting. performance
Source sentence
it is found that all of the models consistently reach above 50% in directional bias forecasting for the stock market.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 22 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.