p–ISSN: 2723 - 6609 e-ISSN: 2745-5254

Vol. 5, No. 5 Mei 2024 http://jist.publikasiindonesia.id/

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2098

Predictive Analysis of Indonesian Stock Market Prices Using

Deep Learning: An Application of Diffusion Variational

Autoencoders

Ardisurya

Universitas Indonesia Depok, Indonesia

Email: [email protected]

*Correspondence

ABSTRACT

Keywords: Diffusion

Variation Autoencoder;

Stock price prediction;

Indonesia stock market;

Deep Learning; Technical

Analysis.

This study introduces the application of the Diffusion

Variational Autoencoder (D-VAE), a deep learning

technique, for predicting stock prices in the Indonesian stock

market. With the challenges presented by market volatility

and complex data distributions, D-VAE is explored for its

capability to encapsulate uncertainty and model complex

distributions. This study is significant as it explores the

potential of D-VAE in the context of the Indonesian stock

market, which has not been widely studied before. Historical

stock data from Yahoo Finance was collected over one year

and preprocessed for training and validation of the model.

The model is trained with an architecture designed to allow

tuning of the latent space, utilising ReLU and linear

activation functions for the encoder and decoder. The

model's performance is evaluated using the Mean Squared

Error (MSE), Mean Absolute Error (MAE), and R-squared

metrics, yielding results that highlight the model's capability

to enhance the accuracy of stock price predictions. By

leveraging machine learning techniques in stock price

prediction models, this study underscores the significant

contribution such approaches can make to informed and

successful investment decisions underpinned by robust data.

Introduction

Stocks are financial instruments that offer investors a fraction of a company's

ownership. Investors who invest in a stock have a high percentage of the profits earned

by the company (Patel, Kumar, & Yadav, 2023). As a vital component in the economy,

the stock market is an indicator of economic health and a platform for companies to

accumulate capital. However, the high volatility of the stock market, influenced by

various factors such as the economy, politics, and social issues, makes stock price

prediction very complex and challenging (Farild, Sawaji, & Poddala, 2023).

The stock market not only acts as an indicator of economic health but also as an

arena for investors to optimise their investment decisions (Al-Alawi & Alaali, 2023).

Accuracy in stock price prediction significantly impacts companies' investment decisions.

Predictive Analysis of Indonesian Stock Market Prices Using Deep Learning: An Application of

Diffusion Variational Autoencoders

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2099

An interesting approach in this regard is the application of the Diffusion Variational

Autoencoder (D-VAE). This deep learning technique can capture uncertainty and model

complex data distributions (Koa, Ma, Ng, & Chua, 2023). Although D-VAE has shown

potential in other domains as an application, its use for stock price prediction in the

Indonesian market has yet to be extensively explored.

Research related to stock price prediction has been growing and pushing

computational intelligence to encourage the enhancement of prediction model

performance further (Shen & Shafiq, 2020). Technical analysis, which predicts stock

prices based on historical data such as stock trading volume and price movements, and

approaches such as ARIMA (Islam & Nguyen, 2020) and Stochastic Oscillator

(Alviyanil’Izzah et al., 2021), will be utilised in this research using historical stock data

from companies in Indonesia.

On the other hand, the popularity of machine learning in predicting stock prices is

increasing, presenting systems to learn from historical data. Techniques like LSTM (Qiu,

Wang, & Zhou, 2020) and Support Vector Machine (SVM) (Madhusudan, 2020) have

been widely used in stock price prediction. This research aims to bridge a gap in the

literature by critically evaluating and applying D-VAE for stock price prediction in the

Indonesian market, offering new insights into the potential of D-VAE in this context(Nath

& Shakhari, n.d.).

Integrating machine learning, especially D-VAE, and technical analysis is expected

to yield more accurate and effective stock price prediction models for the Indonesian

stock market, making a valuable contribution to data-based investment decision-making.

Research Methods

This study was designed to test a stock price prediction model for the Indonesian

stock market using the Diffusion Variational Autoencoder (D-VAE). This approach

combines Deep Learning techniques with technical analysis to understand and predict the

dynamics of stock prices in the Indonesian stock market.

Data Collection and Preparation

The data used in this study is from Yahoo Finance—the period they have taken

ranges from January 1st, 2022, to January 1st, 2023. The data consists of the columns for

the opening (Open), highest (High), lowest (Low), closing (Close) prices, and the trading

volume (Volume) of stocks in the Indonesian stock market. The collected data was then

processed to eliminate any missing data. We extracted relevant features from this data to

construct the model and the target for predictions. These features include the opening,

highest, lowest prices, and trading volume. Then, for the closing price, it becomes the

prediction target. Before feeding the data into the mel, we normalised the feature andarget

using MiMaxScaer. T steps cruciao nsmore stable d ffii earng the matheatical mode us t

normalie hedta:X

Scaled

X- X

min

max

-X

min

y

Scal

y- y

min

max

-y

min

Ardisurya

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2100

Where the value X represents the actual value of the feature to be normalised. For

Xmin, it is the minimum value of each feature in the data, serving as the lower reference

value for normalisation. Similarly, Xmax is the maximum value of each feature in the

data, serving as the upper reference value for normalisation. The value Xscaled is the

normalised value of the feature. The normalisation process changes the actual data to a

scale from 0 to 1.

While y represents the actual value of the target to be normalised, for men, it is the

smallest value among all the target values in the data. This value serves as the lower

reference point for the range of normalisation. For max, it is the most significant value

among all the target values in the data. This value serves as the upper reference point for

the range of normalisation. Finally, scale is the normalised target value. The result of this

normalisation process changes the original data into a scale from 0 to 1.

Diffusion Variational Autoencoder (D-VAE) Model Architecture

The developed D-VAE model is based on a tunable latent space architecture that

consists of an encoder and a decoder. The encoder captures the complex relationships

among the numerous features of the volatile stock market and outputs a prediction of the

closing price. The encoder operates as a data compression mechanism, encoding the input

data into a more compact representation within the latent space. This compression to a

more succinct representation is accomplished through a series of hidden layers. The input

layer receives the input, matching the number of features used. This serves as the entry

point into the D-VAE model. As for the hidden layers, they consist of multiple layers with

neuron units varying in number. These layers have the Rectified Linear Unit (ReLU)

activation function. ReLU is chosen because it does not activate at negative input values,

which can help mitigate the vanishing gradient problem, as the derivative of the ReLU

function remains constant for all positive inputs, thus facilitating a more efficient training

process.

󰇛

󰇜

=max(0,x)

In the ReLU activation function used in the D-VAE architecture, the variable x

represents the input for the ReLU function. The previous layer's output within the neural

network is used as the input for the ReLU function. If the output (f(x)) is higher than zero,

it will equal the input value; if less, it will be zero. This ensures that the output will always

be non-negative. If x is positive, f(x) will be equal to x, but if x is negative, f(x) will be

zero. This helps address the vanishing gradient problem because the derivative of the

ReLU function is consistent for all positive values, thus ensuring efficient

backpropagation during training.

The decoder layer operates as a mechanism to extract the compressed representation

from the encoder and reconstruct the original expected output. This is the inverse process

of the encoder. The decoder architecture mirrors that of the encoder but in reverse order.

The main difference in its implementation is that it aims to gradually expand the succinct

representation from the encoder back to its original form that is more detailed and specific

to the prediction target.

Predictive Analysis of Indonesian Stock Market Prices Using Deep Learning: An Application of

Diffusion Variational Autoencoders

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2101

f(x) = x

The output layer consists of a single neuron with a linear activation function. This

function maintains the input value without any changes, allowing the model to predict

continuous values. In the context of stock price prediction, the model can produce a

prediction value that is sufficiently accurate for the stock's closing price.

Training and Evaluation of the Model

The Diffusion Variational Autoencoder (D-VAE) model is trained using normalised

data to ensure all features are on the same scale. This approach can improve the model's

ability to capture patterns and trends present in the data more effectively.

We employed the Adaptive Moment Estimation (Adam) algorithm to optimise.

Adam is an optimisation algoriththat calculates the learning rates from the scond moment

of grient using RMSPro. It computes adptive earning ratesfor eac parameter by cnsidering

the firt an second estimates of the the graie..

󰆚

t+1

= θ







The value θ represents the model parameters or the weights of the model. These are

the values we aim to ooptimise Then, η represents the learning rate. When changing the

model parameters, this scalar value adjusts the step size during each iteration. The te m



represents the first estimate of the gradient. It is the average of the gradient of the loss

function concerning the model parameters. This helps to adjust the learning rate

adaptively for each parameter. Then, the te v

 represents the second estimate of the

gradient or the uncentered variance of the gradient. The average of the squared gradient

provides an estimate of the gradient variability ofthe lvaluesunctilarto m

he value v

 ed

to adjust the learning rate for each parameter while considering the scale of the gradient.

Finally, the value  is a small constant added to prevent didivisiony zro when dividing b

thesquare root ftthe thehe



.. e employ Mean Squared Error (MSE), Mean Absolute

Error (MAE), and R-squared to evaluate the model used.

(y

-y

)

󰆚

i=1

MSE is calculated as the average of the squares of the differences between actual

and predicted values. It measures how close the predictions are to the actual values. The

value yi represents the stock's actual value being predicted. Then, y _i represents the

predicted value. Moreover, 'n' is the number of samples in tis experiment



-y

|

i=1

MAE measures the average absolute error between predictions and actual values.

Unlike MSE, MAE provides a more linear perspective on prediction errors. The value yi

represents the stock's actual value being predicted. Then, y _i represents the predicted

value. Moreover, 'n' is the number of samples in this experiment.







Ardisurya

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2102

E represents the actual average value, model evaluation is performed by calculating

this metric on the test dataset. It provides a comprehensive picture of the model's

performance in predicting stock prices, considering various aspects of error and accuracy.

Results and Discussion

Model Evaluation Results

The Diffusion Variational Autoencoder (D-VAE) model has been tested on several

Indonesian stocks. The evaluation results show that the model can follow stock price

trends relatively well. The graphs presented are comparisons between the actual stock

prices and the predicted stock prices. These graphs visually represent several companies'

stock performance on the Indonesian stock market (Mukherjee et al., & De, 2023).

Fig 1 Comparison Chart of Actual 'Close' Stock Prices With Predicted 'Close' Stock

Prices in Several Companies Stocks

The graphs displayed compare the actual stock prices and those resulting from

predictions. These graphs visually represent the performance of several companies' stocks

Predictive Analysis of Indonesian Stock Market Prices Using Deep Learning: An Application of

Diffusion Variational Autoencoders

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2103

in the Indonesian stock market, such as PT Bank Central Asia Tbk (BBCA), PT Bank

Negara Indonesia (Persero) Tbk (BBNI), PT Bank Mandiri (Persero) Tbk (BBNI), PT

Adaro Energy Indonesia Tbk (ADRO), PT Aneka Tambang Tbk (ANTM), PT Bukit

Asam Tbk (PTBA). From these graphs, the model accurately follows the general market

trends. However, there are specific periods where the predictions do not align with the

actual values, particularly during periods of high market volatility.

Table 1

Comparison of MSE, MAE, and R-squared Values from Several Companies

The observed fluctuations in MSE and MAE values suggest that the model may

require more specific adjustments or tuning for each stock. In some cases, the model

predicts well, showing more minor errors and higher accuracy, while in others, more

significant prediction errors indicate areas where the model can be improved. This could

involve incorporating more features into the model or combining other machine-learning

techniques.

Consistently high R-squared values indicate that the model can reasonably explain

the variability in stock price data. Although our model is good at summarizing the data

explained, there are volatility periods where the model fails to capture price movements

accurately, indicating the need for more investigation into how the model can be adjusted

to be more sensitive to sudden market changes.

In analyzing the evaluation metrics, we found that although there were variations

in MSE and MAE among different stocks, the model consistently showed a high R2 value

across all the data examined. This indicates that the model accurately captures the

variances within the stock market data. However, the R-squared value does not always

reflect the variability of the actual stock market values. Hence, while it indicates the

model can capture the general trend, specific predictions may diverge from the actual

values, particularly during periods of market volatility.

The variation in MSE and MAE values points to the need for further refinement and

adjustment of the model, mainly when predicting during volatile periods, as discussed in

(Gangwar, Kumar, & Bijpuria, 2021), where hyperparameter tuning improved stock price

prediction accuracy. Similarly, the work by (Stoean, Paja, Stoean, & Sandita, 2019)

showed that integrating additional market sentiment data and indicators could make the

model more sensitive to market dynamics.

Stock MSE MAE R2

PT Bank Central Asia Tbk (XIDX:BBCA) 3155,4965 46,4066 0,9364

PT Bank Negara Indonesia (Persero) Tbk (XIDX:BBNI) 1119,1449 27,0061 0,9501

PT Bank Mandiri (Persero) Tbk (XIDX:BMRI) 2824,7450 93,7510 0,9401

PT Adaro Energy Indonesia Tbk (XIDX:ADRO) 1244,5671 29,2958 0,9425

PT Aneka Tambang Tbk (XIDX:ANTM) 378,9566 15,6345 0,9497

PT Bukit Asam Tbk (XIDX:PTBA) 902,4240 21,2658 0,9847

Average 1604,2223 38,8933 0,9506

Ardisurya

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2104

Further research by (Kumar et al., 2023) suggests that using different machine

learning algorithms that account for different aspects of the data can enhance model

responsiveness and improve predictions during volatile market conditions. This

reinforces the idea that various machine learning techniques can provide a deeper insight

into data analysis.

Given these findings, there are opportunities to further improve the D-VAE model

with ensemble methods, where the prediction of several models can be combined to

achieve a more robust outcome. Moreover, future studies may explore modifications in

the D-VAE architecture, such as adding or reducing the number of neuron layers or

applying techniques like regularization to prevent overfitting and enhance the model's

generalization.

Conclusion

The application of the Diffusion Variational Autoencoder (D-VAE) technique to

predict stock prices in the Indonesian stock market has demonstrated the potential of this

approach. With the implementation of deep learning and machine learning

methodologies, this research has contributed to exploring complex data within the volatile

market. The D-VAE model has shown significant capabilities in following the stock

market trends and has produced good prediction accuracy for various stocks. Evaluation

metrics such as MSE, MAE, and R-squared have varied between stocks, reflecting the

intrinsic stock market variability. Despite variations in MSE and MAE values across

different stocks, a consistently high R-squared value suggests that the model performs

well in capturing the trends within the market. However, a high R-squared value does not

directly reflect the precision of the stock price predictions, especially during periods of

high market volatility.

This study also identifies the need for further refinement and specificity in the

model for individual stocks and market conditions. Additional factors like economic

indicators and market sentiment should be integrated to enhance the model's predictions.

The value of D-VAE lies in its capacity for more detailed training and its potential to

provide a stronger foundation for investment decisions based on robust predictions.

Despite the need for further improvements, the existing model has demonstrated the

ability to provide valuable insights for financial analysts, aiding investors in making more

informed and accurate investment decisions based on stock price predictions.

Bibliography

Al-Alawi, Adel Ismail, & Alaali, Yusuf Ahmed. (2023). Stock Market Prediction using

Predictive Analysis of Indonesian Stock Market Prices Using Deep Learning: An Application of

Diffusion Variational Autoencoders

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2105

Machine Learning Techniques: Literature Review Analysis. 2023 International

Conference On Cyber Management And Engineering (CyMaEn), 153–157. IEEE.

Alviyanil’Izzah, Nur, Martia, Dina Yeni, Imaculata, Maria, Hidayatullah, Moh Iqbal,

Pradana, Andhika Bagus, Setiyani, Diyah Ayu, & Sapuri, Enes. (2021). Analisis

Teknikal Pergerakan Harga Saham Dengan Menggunakan Indikator Stochastic

Oscillator Dan Weighted Moving Average. Keunis, 9(1), 36–53.

https://doi.org/10.32497/keunis.v9i1.2307

Farild, Miftha, Sawaji, Muh Izzulhaq, & Poddala, Paramita. (2023). Analisis teknikal

sebagai dasar pengambilan keputusan dalam transaksi saham. FORUM EKONOMI:

Jurnal Ekonomi, Manajemen Dan Akuntansi, 25(4), 734–739.

Gangwar, Abhinav, Kumar, Ayush, & Bijpuria, Eshikha. (2021). Stock Price Prediction

using Machine Learning. 2021 3rd International Conference on Advances in

Computing, Communication Control and Networking (ICAC3N), 189–193. IEEE.

Islam, Mohammad Rafiqul, & Nguyen, Nguyet. (2020). Comparison of financial models

for stock price prediction. Journal of Risk and Financial Management, 13(8), 181.

Koa, Kelvin J. L., Ma, Yunshan, Ng, Ritchie, & Chua, Tat Seng. (2023). Diffusion

Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock

Price Prediction. Proceedings of the 32nd ACM International Conference on

Information and Knowledge Management, 1087–1096.

https://doi.org/10.1145/3583780.3614844

Kumar, Amodh, Hooda, Susheela, Gill, Rupali, Ahlawat, Deepak, Srivastva, Durgesh, &

Kumar, Raju. (2023). Stock Price Prediction Using Machine Learning. 2023

International Conference on Computational Intelligence and Sustainable

Engineering Solutions (CISES), 926–932. IEEE.

Madhusudan, Desai Mitesh. (2020). Stock Closing Price Prediction Using Machine

Learning SVM Model. International Journal for Research in Applied Science and

Engineering Technology.

Mukherjee, Somenath, Sadhukhan, Bikash, Sarkar, Nairita, Roy, Debajyoti, & De,

Soumil. (2023). Stock market prediction using deep learning algorithms. CAAI

Transactions on Intelligence Technology, 8(1), 82–94.

Nath, Om, & Shakhari, Swapan. (n.d.). Stock Market Prediction Techniques: A

Literature.

Patel, Vikas, Kumar, Ashwani, & Yadav, Deepak. (2023). Machine Learning Techniques

for Predicting Stock Closing Prices. 2023 3rd International Conference on

Pervasive Computing and Social Networking (ICPCSN), 447–452.

https://doi.org/10.1109/ICPCSN58827.2023.00079

Qiu, Jiayu, Wang, Bin, & Zhou, Changjun. (2020). Forecasting stock prices with long-

Ardisurya

Jurnal Indonesia Sosial Teknologi, Vol. 5, No. 5, Mei 2024 2106

short term memory neural network based on attention mechanism. PloS One, 15(1),

e0227222.

Shen, Jingyi, & Shafiq, M. Omair. (2020). Short-term stock market price trend prediction

using a comprehensive deep learning system. Journal of Big Data, 7, 1–33.

Stoean, Catalin, Paja, Wiesław, Stoean, Ruxandra, & Sandita, Adrian. (2019). Deep

architectures for long-term stock price prediction with a heuristic-based strategy for

trading simulations. PloS One, 14(10), e0223593.