Predicting the Nikkei 225 Using Machine Learning: An Empirical Comparison

Abstract

This study compares the predictive performance of multiple machine learning models for forecasting the closing price of the Nikkei 225 on the forecast day using daily data. Five models—Random Forest Regression, Decision Tree Regression, XGBoost Regression, LightGBM Regression, and K-Nearest Neighbors Regression—are employed. In addition to baseline models that use lags of the closing price as explanatory variables, three additional testing models are constructed by adding lags of the opening, high, and low prices individually to the explanatory variables of the baseline models. Furthermore, six different forecast target periods, ranging from five to ten years, are considered, and predictive performance is evaluated using the R-squared value, mean absolute error, and root mean squared error. The results show that Random Forest Regression and Decision Tree Regression exhibit relatively high predictive performance, followed by K-Nearest Neighbors Regression. In addition, the results indicate that adding lags of the opening, high, and low prices to the explanatory variables slightly improves predictive performance in some cases. Furthermore, predictive performance tends to improve as the forecast target period becomes longer. These findings suggest that, in forecasting the closing price of the Nikkei 225, predictive performance may be influenced not only by the type of model but also by the composition of explanatory variables and the forecast target period.

Share and Cite:

Tsuji, C. (2026) Predicting the Nikkei 225 Using Machine Learning: An Empirical Comparison. iBusiness, 18, 159-172. doi: 10.4236/ib.2026.183009.

1. Introduction

In recent years, artificial intelligence (AI) has attracted growing attention as a promising approach to time-series forecasting, with an increasing number of studies exploring and discussing its applications across various domains (e.g., Chen, 2023; Vishwas et al., 2025; Tsuji, 2026). Stock price prediction is one of the important research topics in financial markets, and a wide range of forecasting methods have been examined, from statistical approaches to machine learning and, more recently, deep learning. Because stock prices and stock returns exhibit complex nonlinearities and temporal dependencies, recent studies have employed machine learning models such as Random Forest, Decision Tree, Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), as well as deep learning models such as Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), with the aim of capturing these characteristics (e.g., Jiang et al., 2019; Tsuji, 2022, 2025).

Previous studies have examined the effectiveness of deep learning models, including LSTM, as well as the possibility of utilizing information other than prices, such as investor sentiment on social media (e.g., Liu et al., 2023). In addition, research has progressed on addressing the non-stationarity of financial time series and on the generalization performance of models across different markets (e.g., Hong et al., 2023).

On the other hand, when using time-series information from stock prices themselves, there remains room for further investigation into the extent to which different machine learning models exhibit different predictive performance and how predictive performance changes depending on the sample period and the specification of explanatory variables.

This study therefore applies five machine learning models—Random Forest Regression, Decision Tree Regression, XGBoost Regression, LightGBM Regression, and K-Nearest Neighbors Regression—to daily Nikkei 225 data to forecast the closing price on the forecast day and compare their predictive performance. As shown in Figure 1, the Nikkei 225 has exhibited a pronounced upward trend in recent years, making it a useful benchmark for evaluating and comparing different forecasting models. In addition, this study uses a model that includes only lags of the closing price as explanatory variables, which serves as the baseline model, and compares its predictive performance with that of models that additionally include lags of the opening, high, and low prices.

Furthermore, six different forecast target periods, ranging from five to ten years, are considered to examine the effects of differences in the forecast target period on the prediction results. The objective of this study is to empirically clarify, through these comparisons, the relative predictive performance of the respective machine learning models in forecasting the closing price of the Nikkei 225 and the differences in predictive performance resulting from the specification of explanatory variables and forecast target periods.

The results of the analysis show broadly similar tendencies across different forecast target periods for each of the three evaluation measures, the R-squared value (R2), mean absolute error (MAE), and root mean squared error (RMSE). In particular, Random Forest Regression and Decision Tree Regression exhibit relatively high predictive performance, followed by K-Nearest Neighbors Regression.

In addition, adding lags of the opening, high, and low prices to the lags of the closing price as explanatory variables is found to slightly improve predictive performance in some cases. Furthermore, comparison across different forecast target periods indicates that predictive performance tends to improve as the period is extended from five to ten years. These findings are significant contributions of this study.

The remainder of this paper is organized as follows. Section 2 reviews the previous literature, and Section 3 describes the data and models. Section 4 presents the empirical results, followed by the conclusion in Section 5.

Figure 1. Evolution of the Nikkei 225 closing prices: January 5, 1970, to December 30, 2025.

2. Previous Studies

In recent years, research on stock price prediction has progressed through the use of machine learning and deep learning in addition to conventional statistical methods. An increasing number of studies have employed neural networks such as LSTM and CNN to capture the complex nonlinearities and time-series characteristics of stock prices and stock returns. This section reviews previous studies on stock price prediction using AI in chronological order.

Roondiwala et al. (2017) applied LSTM to stock index prediction and demonstrated the usefulness of Recurrent Neural Networks (RNNs) and LSTM for time-series data such as stock prices. This study is important in that it indicated the potential effectiveness of LSTM, which can learn long-term dependencies, for predicting future price movements using historical stock price information.

Subsequently, Jiang et al. (2019) presented an approach for classifying stock price increases and decreases by combining large-scale data processing using Spark with machine learning models such as Random Forest and Decision Tree. This demonstrated the potential for applying not only deep learning but also conventional machine learning models to large-scale financial data.

Moreover, Moghar and Hamiche (2020) examined stock time-series forecasting using LSTM and found that the number of training iterations and the period of data used affected predictive performance. These studies indicate that, in stock price prediction, not only the choice of models that appropriately capture the characteristics of time-series data but also training conditions and data handling have important effects on predictive accuracy.

Later, Mokhtari et al. (2021) examined the potential of utilizing AI and machine learning in stock market analysis by incorporating sentiment analysis of posts on Twitter in addition to technical analysis based on historical stock price data. In this way, the information used for stock price prediction has expanded from market data such as prices and trading volume to unstructured data containing investors’ opinions and emotions.

Furthermore, Liu et al. (2023) applied Natural Language Processing (NLP) to a large volume of social media data and quantified investor sentiment to analyze the relationship between sentiment and stock prices. Their results showed a significant positive synergy between investor sentiment and stock prices, while also indicating that this relationship could reverse or disappear depending on the period. In addition, the study showed that investor sentiment on social media reflects expectations regarding future market trends, suggesting the potential usefulness of sentiment information for stock price prediction.

Moreover, Hong et al. (2023) focused on the non-stationarity of financial time series and proposed a forecasting model for non-stationary financial time series using meta-learning. In this model, CNN is used as the predictor and LSTM as the meta-learner, and long-term non-stationary time series are divided into multiple shorter subsequences for forecasting. The experiments showed that the proposed model achieved better predictive performance than conventional CNN and autoregressive (AR) models, demonstrating the effectiveness of an adaptive forecasting approach for non-stationary financial data.

Subsequently, Ghosh et al. (2024) compared multiple neural network architectures, including Multilayer Perceptron (MLP), RNN, LSTM, and CNN, examined their respective stock price forecasting performance, and analyzed the applicability of forecasting models to different markets. This indicates that, in addition to accuracy for a particular market or dataset, the generalization performance of models is also an important research issue. Furthermore, Abir et al. (2025) applied CNN, LSTM, and hybrid models combining these approaches to financial markets in the BRICS countries, thereby extending the application of deep learning models to multiple countries and markets.

These studies indicate that research on stock price prediction has evolved from forecasting based on a single time series toward forecasting in non-stationary market environments and different markets, as well as forecasting using combinations of multiple deep learning models. However, relatively few studies have carefully examined well-established models by changing settings such as forecast target periods and explanatory variables. Therefore, we believe that research such as the present study fills the research gap left by existing studies and thus is highly meaningful.

3. Data and Models

This section describes the data used in the analysis and the forecasting models. This study employs the five machine learning models, Random Forest Regression, Decision Tree Regression, XGBoost Regression, LightGBM Regression, and K-Nearest Neighbors Regression, for model comparisons.

The analysis uses daily data for the Nikkei 225. Specifically, the four daily price variables—opening price (Open), high price (High), low price (Low), and closing price (Close)—are used. The overall sample period used in the analysis is from January 5, 1970, to December 30, 2025. To clarify the differences by forecasting periods, six forecast target periods are considered: five years from January 4, 2021, to December 30, 2025; six years from January 6, 2020, to December 30, 2025; seven years from January 4, 2019, to December 30, 2025; eight years from January 4, 2018, to December 30, 2025; nine years from January 4, 2017, to December 30, 2025; and ten years from January 4, 2016, to December 30, 2025. Each of these six periods is analyzed separately for the five machine learning models.

Accordingly, in model training and prediction, for each of the six period settings, the observations outside the respective forecast target period within the overall sample period constitute the training period, while the respective forecast target period constitutes the test period.

The prediction target is the closing price (Close) of the Nikkei 225. First, taking into account the temporal relationship with the closing price, a baseline model is specified using lags 1 through 3 of the closing price as explanatory variables. Moreover, three additional six-variable models are constructed by adding lags 0 through 2 of the opening price (Open), lags 1 through 3 of the high price (High), and lags 1 through 3 of the low price (Low), respectively, to the explanatory variables of the baseline model.

These four explanatory-variable specifications are then applied to the five forecasting models described above for comparative analysis. For lag 0 of Open, it is assumed that the opening price of the day is known at the time of prediction. In other words, the analysis assumes that the closing price of the day is predicted once the opening price of that day becomes known.

4. Results

This section compares and examines the results obtained from each forecasting model. The five models—Random Forest Regression, Decision Tree Regression, XGBoost Regression, LightGBM Regression, and K-Nearest Neighbors Regression—are applied to the price series of the Nikkei 225 and compared across six forecast target periods of five, six, seven, eight, nine, and ten years. The results for the predictive accuracy of each period are presented in Tables 1-6, respectively. For all forecasting models, model specifications were determined based solely on data from the training period, and observations from the forecast target period were not used for model fitting.

Each of the six tables presents the results of forecasting the closing price on the forecast day using past 3-day closing prices as explanatory variables in Panel A; the results of forecasting using past 3-day closing prices and same-day and past 2-day opening prices as explanatory variables in Panel B; the results of forecasting using past 3-day closing prices and past 3-day high prices as explanatory variables in Panel C; and the results of forecasting using past 3-day closing prices and past 3-day low prices as explanatory variables in Panel D.

First, across the three evaluation measures—R2, MAE, and RMSE—shown in Tables 1-6, broadly similar tendencies are observed with respect to the predictive accuracy of the daily closing price of the Nikkei 225 across the six forecast target periods. In particular, Random Forest Regression and Decision Tree Regression exhibit relatively high predictive accuracy, followed by K-Nearest Neighbors Regression. In contrast, XGBoost Regression and LightGBM Regression underperform the other three models.

Furthermore, as shown in Tables 1-6, adding lags of Open, High, or Low as explanatory variables to the baseline models, which use only lags of Close as explanatory variables, slightly improves predictive accuracy in some cases. At the same time, predictive accuracy tends to improve as the forecast target period is extended from five to ten years. As the values of R2, MAE, and RMSE in Tables 1-6 indicate, these tendencies remain highly consistent across the six forecast target periods.

Table 1. Results of 5-year forecasts of the Nikkei 225 daily closing prices.

Panel A. Forecasting using Past 3-day Close Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.81558

1090.59975

2699.75107

Decision Tree Regression

0.81534

1158.90021

2701.51411

XGBoost Regression

0.80763

1145.36361

2757.31333

LightGBM Regression

0.77703

1325.91695

2968.57030

K-Nearest Neighbors Regression

0.81390

1106.53505

2712.00109

Panel B. Forecasting using Past 3-day Close Prices and Same-day and Past 2-day Open Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.81518

1036.34562

2702.69431

Decision Tree Regression

0.81772

1080.98340

2684.01892

XGBoost Regression

0.80336

1124.99080

2787.77702

LightGBM Regression

0.77843

1281.49296

2959.21338

K-Nearest Neighbors Regression

0.81506

1066.78127

2703.54347

Panel C. Forecasting using Past 3-day Close Prices and Past 3-day High Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.81481

1094.83399

2705.39066

Decision Tree Regression

0.81566

1139.68042

2699.16368

XGBoost Regression

0.80884

1137.45201

2748.64161

LightGBM Regression

0.78029

1310.28690

2946.79702

K-Nearest Neighbors Regression

0.81357

1111.38107

2714.43792

Panel D. Forecasting using Past 3-day Close Prices and Past 3-day Low Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.81428

1098.52381

2709.27923

Decision Tree Regression

0.81575

1146.51763

2698.49230

XGBoost Regression

0.79907

1187.41044

2817.98405

LightGBM Regression

0.77660

1331.12153

2971.37893

K-Nearest Neighbors Regression

0.81374

1112.94727

2713.16110

Notes. Our full sample period is from January 5, 1970, to December 30, 2025, and the test period is from January 4, 2021, to December 30, 2025. R2 denotes the R-squared value, MAE denotes mean absolute error, and RMSE denotes root mean squared error.

Table 2. Results of 6-year forecasts of the Nikkei 225 daily closing prices.

Panel A. Forecasting using Past 3-day Close Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.87709

953.59991

2469.86650

Decision Tree Regression

0.87660

1015.37587

2474.73816

XGBoost Regression

0.86773

1018.05453

2562.19506

LightGBM Regression

0.85150

1148.36613

2714.82237

K-Nearest Neighbors Regression

0.87586

971.34155

2482.21023

Panel B. Forecasting using Past 3-day Close Prices and Same-day and Past 2-day Open Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.87701

892.75023

2470.65750

Decision Tree Regression

0.87836

957.24588

2457.11892

XGBoost Regression

0.86824

975.42374

2557.23526

LightGBM Regression

0.85204

1115.51635

2709.90466

K-Nearest Neighbors Regression

0.87681

927.37058

2472.69466

Panel C. Forecasting using Past 3-day Close Prices and Past 3-day High Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.87644

958.91135

2476.38175

Decision Tree Regression

0.87678

1009.06895

2472.95892

XGBoost Regression

0.87026

999.86801

2537.58512

LightGBM Regression

0.85397

1132.79038

2692.17424

K-Nearest Neighbors Regression

0.87566

973.01612

2484.19373

Panel D. Forecasting using Past 3-day Close Prices and Past 3-day Low Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.87614

960.36123

2479.36198

Decision Tree Regression

0.87678

1011.04136

2472.99860

XGBoost Regression

0.86593

1022.77689

2579.53995

LightGBM Regression

0.85138

1147.95385

2715.91793

K-Nearest Neighbors Regression

0.87572

978.16133

2483.63770

Notes. Our full sample period is from January 5, 1970, to December 30, 2025, and the test period is from January 6, 2020, to December 30, 2025. R2 denotes the R-squared value, MAE denotes mean absolute error, and RMSE denotes root mean squared error.

Table 3. Results of 7-year forecasts of the Nikkei 225 daily closing prices.

Panel A. Forecasting using Past 3-day Close Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.90405

844.08330

2290.88025

Decision Tree Regression

0.90394

902.13725

2292.22219

XGBoost Regression

0.89615

903.88740

2383.34565

LightGBM Regression

0.88434

1012.03101

2515.24671

K-Nearest Neighbors Regression

0.90314

857.97267

2301.71220

Panel B. Forecasting using Past 3-day Close Prices and Same-day and Past 2-day Open Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.90413

781.53646

2289.97819

Decision Tree Regression

0.90498

851.60917

2279.81889

XGBoost Regression

0.89849

845.16203

2356.29358

LightGBM Regression

0.88499

969.74541

2508.12516

K-Nearest Neighbors Regression

0.90393

814.64290

2292.37096

Panel C. Forecasting using Past 3-day Close Prices and Past 3-day High Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.90369

845.48256

2295.23088

Decision Tree Regression

0.90415

891.99150

2289.68040

XGBoost Regression

0.89831

884.69800

2358.42492

LightGBM Regression

0.88627

996.49204

2494.20091

K-Nearest Neighbors Regression

0.90298

858.82289

2303.62538

Panel D. Forecasting using Past 3-day Close Prices and Past 3-day Low Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.90361

845.97694

2296.21487

Decision Tree Regression

0.90369

905.85974

2295.14861

XGBoost Regression

0.89890

883.09870

2351.59734

LightGBM Regression

0.88557

990.26859

2501.81596

K-Nearest Neighbors Regression

0.90303

864.07701

2303.10238

Notes. Our full sample period is from January 5, 1970, to December 30, 2025, and the test period is from January 4, 2019, to December 30, 2025. R2 denotes the R-squared value, MAE denotes mean absolute error, and RMSE denotes root mean squared error.

Table 4. Results of 8-year forecasts of the Nikkei 225 daily closing prices.

Panel A. Forecasting using Past 3-day Close Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.91608

764.73614

2144.23134

Decision Tree Regression

0.91554

827.94652

2151.05330

XGBoost Regression

0.90858

820.99140

2238.01718

LightGBM Regression

0.89983

892.66862

2342.59752

K-Nearest Neighbors Regression

0.91522

778.49900

2155.20648

Panel B. Forecasting using Past 3-day Close Prices and Same-day and Past 2-day Open Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.91623

702.71275

2142.37098

Decision Tree Regression

0.91627

793.26870

2141.77253

XGBoost Regression

0.91055

763.68722

2213.80165

LightGBM Regression

0.90048

856.20747

2334.99461

K-Nearest Neighbors Regression

0.91599

734.63173

2145.38275

Panel C. Forecasting using Past 3-day Close Prices and Past 3-day High Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.91582

763.99030

2147.49936

Decision Tree Regression

0.91559

818.30517

2150.50203

XGBoost Regression

0.91161

803.66639

2200.58138

LightGBM Regression

0.90138

879.29435

2324.44428

K-Nearest Neighbors Regression

0.91510

780.67689

2156.75410

Panel D. Forecasting using Past 3-day Close Prices and Past 3-day Low Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.91561

767.57620

2150.25795

Decision Tree Regression

0.91549

831.16630

2151.80460

XGBoost Regression

0.91290

800.84445

2184.42320

LightGBM Regression

0.89993

891.74273

2341.41941

K-Nearest Neighbors Regression

0.91513

782.84788

2156.26945

Notes. Our full sample period is from January 5, 1970, to December 30, 2025, and the test period is from January 4, 2018, to December 30, 2025. R2 denotes the R-squared value, MAE denotes mean absolute error, and RMSE denotes root mean squared error.

Table 5. Results of 9-year forecasts of the Nikkei 225 daily closing prices.

Panel A. Forecasting using Past 3-day Close Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.92820

696.13137

2021.66512

Decision Tree Regression

0.92738

768.63354

2033.15572

XGBoost Regression

0.92384

735.73993

2082.04861

LightGBM Regression

0.91517

807.51863

2197.44445

K-Nearest Neighbors Regression

0.92748

708.07887

2031.68122

Panel B. Forecasting using Past 3-day Close Prices and Same-day and Past 2-day Open Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.92834

637.93423

2019.58642

Decision Tree Regression

0.92838

723.21554

2019.06665

XGBoost Regression

0.92319

700.08930

2090.87839

LightGBM Regression

0.91574

758.77877

2189.93906

K-Nearest Neighbors Regression

0.92818

664.56023

2021.94099

Panel C. Forecasting using Past 3-day Close Prices and Past 3-day High Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.92802

693.53387

2024.12561

Decision Tree Regression

0.92771

752.02628

2028.44275

XGBoost Regression

0.92523

732.34380

2062.94788

LightGBM Regression

0.91608

799.61407

2185.54282

K-Nearest Neighbors Regression

0.92737

710.40317

2033.22502

Panel D. Forecasting using Past 3-day Close Prices and Past 3-day Low Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.92771

698.03494

2028.43264

Decision Tree Regression

0.92778

757.45497

2027.50698

XGBoost Regression

0.92215

745.41652

2104.98440

LightGBM Regression

0.91539

806.53620

2194.49927

K-Nearest Neighbors Regression

0.92739

713.46267

2032.97641

Notes. Our full sample period is from January 5, 1970, to December 30, 2025, and the test period is from January 4, 2017, to December 30, 2025. R2 denotes the R-squared value, MAE denotes mean absolute error, and RMSE denotes root mean squared error.

Table 6. Results of 10-year forecasts of the Nikkei 225 daily closing prices.

Panel A. Forecasting using Past 3-day Close Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.94133

646.52942

1919.57260

Decision Tree Regression

0.94056

719.34984

1931.99684

XGBoost Regression

0.93599

694.16319

2004.87671

LightGBM Regression

0.93060

745.66403

2087.65692

K-Nearest Neighbors Regression

0.94071

658.97482

1929.55019

Panel B. Forecasting using Past 3-day Close Prices and Same-day and Past 2-day Open Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.94149

589.63178

1916.80362

Decision Tree Regression

0.94151

670.22412

1916.49787

XGBoost Regression

0.93976

629.21047

1944.94714

LightGBM Regression

0.93162

694.33715

2072.24427

K-Nearest Neighbors Regression

0.94132

616.34753

1919.68910

Panel C. Forecasting using Past 3-day Close Prices and Past 3-day High Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.94114

645.79033

1922.53939

Decision Tree Regression

0.94080

707.27427

1928.14411

XGBoost Regression

0.93625

694.92244

2000.89342

LightGBM Regression

0.93128

740.83249

2077.34107

K-Nearest Neighbors Regression

0.94063

661.36332

1930.93430

Panel D. Forecasting using Past 3-day Close Prices and Past 3-day Low Prices

Model

Forecasting Performance

R2

MAE

RMSE

Random Forest Regression

0.94105

647.33798

1924.10647

Decision Tree Regression

0.94083

712.88133

1927.71269

XGBoost Regression

0.93822

678.37639

1969.74899

LightGBM Regression

0.93085

743.93305

2083.95292

K-Nearest Neighbors Regression

0.94064

663.65923

1930.76031

Notes. Our full sample period is from January 5, 1970, to December 30, 2025, and the test period is from January 4, 2016, to December 30, 2025. R2 denotes the R-squared value, MAE denotes mean absolute error, and RMSE denotes root mean squared error.

5. Conclusions

This study used daily data for the Nikkei 225 to forecast its closing price using five machine learning models—Random Forest Regression, Decision Tree Regression, XGBoost Regression, LightGBM Regression, and K-Nearest Neighbors Regression—and compared their predictive performance. The analysis employed baseline models using lags of the closing price as explanatory variables, as well as models that added lags of the opening, high, and low prices, respectively, to the explanatory variables of the baseline models. In addition, comparisons were conducted across six forecast target periods ranging from five to ten years.

The results showed broadly similar tendencies across different forecast target periods for each of the three evaluation measures, R2, MAE, and RMSE. In particular, Random Forest Regression and Decision Tree Regression exhibited relatively high predictive performance, followed by K-Nearest Neighbors Regression.

In addition, adding lags of the opening, high, and low prices to the lags of the closing price as explanatory variables slightly improved predictive performance in some cases. This suggests that incorporating information related to intraday price formation, in addition to historical closing-price information, may contribute to improving predictive performance.

Furthermore, comparison across different forecast target periods indicated that predictive performance tends to improve as the period is extended from five to ten years. This result suggests that, when forecasting financial time series such as the Nikkei 225 using machine learning models, the period of data used in the analysis may affect predictive performance.

Overall, this study demonstrated that, in forecasting the daily closing price of the Nikkei 225, not only the type of model but also the composition of explanatory variables and the forecast target period are important factors to consider when evaluating predictive performance. This clarification is the most significant contribution of this study. Moreover, we found that, among the models compared in this study, Random Forest Regression and Decision Tree Regression performed relatively well. This finding is also an important contribution of this study.

This study is a comparative analysis centered on price data for the Nikkei 225, and whether similar results would be obtained for other markets, or when additional information such as trading volume, news, and investor sentiment is incorporated, remains a subject for future research. Nevertheless, the present study highlights the critical importance of meticulous foundational research. From this perspective, we anticipate that the findings of the present study will make a significant contribution to further research in this area and serve as a valuable basis for further investigation.

Acknowledgements

The author is grateful for the repeated cordial invitations from Joy Deng, Managing Editor of the Journal. The author also thanks the anonymous reviewers for their supportive and constructive comments on this paper. Additionally, the author appreciates the financial support from the Chuo University Grant for Special Research. Lastly, the author also thanks all the editors of this journal for their kind attention to this paper.

Author Contributions

The author designed and conducted all of the research.

Conflicts of Interest

The author declares no conflicts of interest regarding the publication of this paper.

References

[1] Abir, S. I., Shoha, S., Al Shiam, S. A., Zakaria, R. M., Shimanto, A. H., Shamsul Arefeen, S. M. et al. (2025). Deep Learning for Financial Markets: A Case-Based Analysis of BRICS Nations in the Era of Intelligent Forecasting. Journal of Economics, Finance and Accounting Studies, 7, 1-15. [Google Scholar] [CrossRef]
[2] Chen, X. (2023). Stock Price Prediction Using Machine Learning Strategies. BCP Business & Management, 36, 488-497. [Google Scholar] [CrossRef]
[3] Ghosh, B. P., Bhuiyan, M. S., Das, D., Nguyen, T. N., Jewel, R. M., Mia, M. T., Cao, D. M., & Shahid, R. (2024). Deep Learning in Stock Market Forecasting: Comparative Analysis of Neural Network Architectures across NSE and NYSE. Journal of Computer Science and Technology Studies, 6, 68-75. [Google Scholar] [CrossRef]
[4] Hong, A., Gao, M., Gao, Q., & Peng, X. (2023). Non-Stationary Financial Time Series Forecasting Based on Meta-Learning. Electronics Letters, 59, e12681. [Google Scholar] [CrossRef]
[5] Jiang, X., Mo, H., & Li, H. (2019). Stock Classification Prediction Based on Spark. Procedia Computer Science, 162, 243-250. [Google Scholar] [CrossRef]
[6] Liu, Q., Lee, W., Huang, M., & Wu, Q. (2023). Synergy between Stock Prices and Investor Sentiment in Social Media. Borsa Istanbul Review, 23, 76-92. [Google Scholar] [CrossRef]
[7] Moghar, A., & Hamiche, M. (2020). Stock Market Prediction Using LSTM Recurrent Neural Network. Procedia Computer Science, 170, 1168-1173. [Google Scholar] [CrossRef]
[8] Mokhtari, S., Yen, K. K., & Liu, J. (2021). Effectiveness of Artificial Intelligence in Stock Market Prediction Based on Machine Learning. International Journal of Computer Applications, 183, 1-8. [Google Scholar] [CrossRef]
[9] Roondiwala, M., Patel, H., & Varma, S. (2017). Predicting Stock Prices Using LSTM. International Journal of Science and Research (IJSR), 6, 1754-1756. [Google Scholar] [CrossRef]
[10] Tsuji, C. (2022). Exchange Rate Forecasting via a Machine Learning Approach. iBusiness, 14, 119-126. [Google Scholar] [CrossRef]
[11] Tsuji, C. (2025). Forecasting Exchange Rates with Artificial Intelligence: A Study of European Currencies. International Business Research, 18, 24-34. [Google Scholar] [CrossRef]
[12] Tsuji, C. (2026). Volatility Estimation and Crash Risk Forecasting Using Unified GARCH Models: Empirical Evidence from the Russian Invasion of Ukraine. Quantitative Finance and Economics, 10, 438-480. [Google Scholar] [CrossRef]
[13] Vishwas, H. N., Usha, B, A., & Sangeetha, K. N. (2025). Artificial Intelligence-Based Stock Market Price Prediction, a Review. Mathematical Models in Engineering, 11, 204-229. [Google Scholar] [CrossRef]

Copyright © 2026 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.