Comparative Analysis of Deep Learning Approaches for Stock Chart Pattern Detection in Technical Analysis

Technical chart patterns are widely used in trading decisions, yet manual identification is subjective and inconsistent. This is evident in market such as the Indonesia Stock Exchange (IDX) where automated pattern recognition research studies are still limited. Therefore, deep learning offers strong capabilities for capturing complex temporal structures in price data, making it suitable for automated chart pattern classification. This study develops deep learning models to classify four continuation patterns using IDX stock price data. Five architectures (ANN, RNN, LSTM, GRU, CNN) are benchmarked and their pairwise ensembles are stacked with XGBoost. Models are trained on normalized price sequences, evaluated through stratified 5-fold cross-validation and trading backtests. Results show that CNN with GRU and GRU with ANN outperform standalone models with F1 scores above 0.99 while backtesting confirms higher risk-adjusted returns and reduced drawdowns when paired with an ExRem signal filter. These findings show that ensemble deep learning improves objective chart pattern detection.

• Publication year

  2025

• Venue

  2025 2nd Beyond Technology Summit on Informatics International Conference (BTS-I2C)

• Publication date

  2025-12-18

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/BTS-I2C67944.2025.11399400
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Financial Markets and ESG: How Big Data is Transforming Sustainable Investing in Developing countries

  2025cited by this paper
• An Advanced Ensemble Deep Learning Framework for Stock Price Prediction Using VAE, Transformer, and LSTM Model

  2025cited by this paper
• Stock price prediction based on hybrid CNN-LSTM model

  2024cited by this paper
• Application of an ANN and LSTM-Based Ensemble Model for Stock Market Prediction

  2024cited by this paper
• Applying ensemble learning to multiple stock price predictions: A comparative study

  2024cited by this paper
• Economic Forces in Stock Returns

  2024cited by this paper
• Applying machine learning algorithms to predict the stock price trend in the stock market – The case of Vietnam

  2024cited by this paper
• A Decision Support System for Stock Selection and Asset Allocation Based on Fundamental Data Analysis

  2024cited by this paper
• Stock Price Prediction using Dynamic Neural Networks

  2023cited by this paper
• MONEY: Ensemble learning for stock price movement prediction via a convolutional network with adversarial hypergraph model

  2023cited by this paper
• Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm

  2023cited by this paper
• Economic state classification and portfolio optimisation with application to stagflationary environments

  2022cited by this paper
• Forecasting turning points in stock price by applying a novel hybrid CNN-LSTM-ResNet model fed by 2D segmented images

  2022cited by this paper
• A Hybrid Model for Stock Price Prediction using Machine Learning Techniques with CNN

  2021cited by this paper
• Artificial Neural Network and Its Application Research Progress in Chemical Process

  2021cited by this paper
• Economic uncertainty and Australian stock returns

  2021cited by this paper
• Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network

  2020cited by this paper
• A CNN-LSTM-Based Model to Forecast Stock Prices

  2020cited by this paper
• A novel ensemble deep learning model for stock prediction based on stock prices and news

  2020cited by this paper
• Global Stock Market Prediction Based on Stock Chart Images Using Deep Q-Network

  2019cited by this paper
• Using Deep Learning Neural Networks and Candlestick Chart Representation to Predict Stock Market

  2019cited by this paper
• Study on the prediction of stock price based on the associated network model of LSTM

  2019cited by this paper
• An innovative neural network approach for stock market prediction

  2018cited by this paper
• A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

  2017cited by this paper
• A dynamic trading rule based on filtered flag pattern recognition for stock market price forecasting

  2017cited by this paper
• Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

  2014cited by this paper
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

  2014cited by this paper
• Stock market trading rule discovery using technical charting heuristics

  2002cited by this paper

• No citing papers are available for this paper.