Algorithmic Trading with Combination of Advanced Technical Indicators – An Automation

Author(s)	Mr. Soumick Adhikary, Mr. Arup Kadia
Country	India
Abstract	A novel deep learning framework for automated stock trading signal generation is proposed, leveraging Exponential Moving Average (EMA) crossover, average traded volume, and Parabolic SAR as feature inputs. The model integrates technical indicators to reduce noise (EMA), validate momentum (volume), and identify trend reversals (Parabolic SAR). These sequential features are processed by a bi-LSTM neural network, which then produces discrete trading signals. Backtesting on daily stock market data post-2020 demonstrates a statistically significant improvement in risk-adjusted returns, higher Sharpe ratios, and lower drawdowns compared to baseline strategies using EMA crossover alone. The inclusion of average traded volume helps filter false signals during low-liquidity periods, while Parabolic SAR enhances early trend reversal detection, especially in trending markets. These findings suggest that hybridizing technical indicators within deep learning architectures can yield superior automated trading performance. The proposed method offers a promising direction for algorithmic trading systems.
Keywords	Deep Learning (DL), Stock Market, Stock Trading, Average Traded Volume (ATV), Parabolic SAR, Algorithmic Trading.
Field	Computer > Data / Information
Published In	Volume 16, Issue 3, July-September 2025
Published On	2025-08-24
DOI	https://doi.org/10.71097/IJSAT.v16.i3.7777
Short DOI	https://doi.org/g9x32f

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology