Assessing Manual Dataset Creation For Xauusd Market Prediction : A Comparative Study Logistic Regression And Decision Tree Model
Abstract
This study aims to develop a simplified dataset for more effective market prediction, focusing on the Forex trading of XAUUSD (Gold/USD). The dataset was gathered from the TradingView platform, covering the period from March 4, 2023, to December 21, 2023. The data collection method involved intensive observation of daily and weekly charts, utilizing Daily and Weekly Moving Average (MA) indicators and the concept of breakout. The analysis focused on measuring the distance between the Daily MA at the beginning and end of the period (start and stop), and utilizing this data for entry strategy in the following three time periods. The trading strategy adopted involves the simultaneous use of Buy and Sell orders, with a Stop Loss (SL) to Take Profit (TP) ratio of 1:2. TP was adjusted to accommodate aggressive price movements, while SL remained constant. The collected data was meticulously recorded and stored in Excel format for further analysis.
With the prepared dataset, this research applies two AI models, Logistic Regression and Decision Tree, to predict the best trading decision – Buy or Sell. The study aims not only to create a useful dataset for market prediction but also to compare the effectiveness of two different AI methods in the context of Forex trading of XAUUSD. The results are expected to provide insights into which model is more accurate and efficient in analyzing and predicting market trends, with practical implications for traders and market analysts.Keywords
Full Text:
PDFReferences
D. R. Meilanova, “Mengenal Perbedaan antara Pasar Saham dan Forex - Finansial Bisnis.com.”
H. P. S. D. Weerathunga and A. T. P. Silva, “DRNN-ARIMA approach to short-term trend forecasting in forex market,” 18th Int. Conf. Adv. ICT Emerg. Reg. ICTer 2018 - Proc., pp. 287–293, 2019, doi: 10.1109/ICTER.8615580.
M. D. Archer, Getting started in currency trading : winning in today’s Forex market. 2010.
B. Lobel, “What is Gold? Understanding Gold as a Trader’s Commodity,” Nov. 07, 2020. https://www.dailyfx.com/education/commodities/what-is-gold.html (accessed May 27, 2021).
H. Jumaidi, “MENGENAL TRADING GOLD/XAU/USD YUK,” 2020. https://astronacci.com/blog/read/mengenal-trading-gold-xau-usd-yuk (accessed May 27, 2021).
K. S. Zarkias, N. Passalis, A. Tsantekidis, and A. Tefas, “Deep Reinforcement Learning for Financial Trading Using Price Trailing,” ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process.- Proc., vol. 2019-May, pp. 3067–3071, 2019, doi: 10.1109/ICASSP.2019.8683161.
P. Oncharoen and P. Vateekul, “Deep Learning for Stock Market Prediction Using Event Embedding and Technical Indicators,” ICAICTA 2018 - 5th Int. Conf. Adv. Informatics Concepts Theory Appl., pp. 19–24, 2018, doi: 10.1109/ICAICTA.2018.8541310.
S. Ahmed, S. U. Hassan, N. R. Aljohani, and R. Nawaz, “FLF-LSTM: A novel prediction system using Forex Loss Function,” Appl. Soft Comput. J., vol. 97, p. 106780, 2020, doi: 10.1016/j.asoc.2020.106780.
B. A. Usha, T. N. Manjunath, and T. Mudunuri, “Commodity and Forex trade automation using Deep Reinforcement Learning,” 1st Int. Conf. Adv. Technol. Intell. Control. Environ. Comput. Commun. Eng. ICATIECE 2019, pp. 27–31, 2019, doi: 10.1109/ICATIECE45860.2019.9063807.
W. Long, Z. Lu, and L. Cui, “Deep learning-based feature engineering for stock price movement prediction,” Knowledge-Based Syst., vol. 164, pp. 163–173, 2019, doi: 10.1016/j.knosys.2018.10.034.
D. Vezeris, T. Kyrgos, and C. Schinas, “Take Profit and Stop Loss Trading Strategies Comparison in Combination with an MACD Trading System,” J. Risk Financ. Manag., vol. 11, no. 3, p. 56, 2018, doi: 10.3390/jrfm11030056.
Chen, M. Y. (2011). Predicting corporate financial distress based on integration of decision tree classification and logistic regression. Expert Systems with Applications, 38(9), 11261–11272. https://doi.org/10.1016/J.ESWA.2011.02.173
Hargreaves, C., & Hao, Y. (2013). Prediction of Stock Performance Using Analytical Techniques. https://doi.org/10.4304/jetwi.5.2.136-142
Zhou, F., Zhang, Q., Sornette, D., & Jiang, L. (2019). Cascading logistic regression onto gradient boosted decision trees for forecasting and trading stock indices. Applied Soft Computing, 84, 105747. https://doi.org/10.1016/J.ASOC.2019.105747
DOI: http://dx.doi.org/10.52155/ijpsat.v42.2.5903
Refbacks
- There are currently no refbacks.
Copyright (c) 2024 Andri Purwoko
This work is licensed under a Creative Commons Attribution 4.0 International License.