King Talal School of Business Technology

Advanced Financial Technology

:Proposal Topic
The Role of AI in Predicting Forex Market
Movements
:By
Zain Al-Omari
Anas Al-Jabi
Supervised by:
Dr. Laith Almaqableh
 1

1- Introduction

In a complex and chaotic world of foreign exchange markets, where currencies are bought and

sold simultaneously. The ability to predict movements and fluctuations that affect trade profitability

within seconds is both a tricky challenge and an attractive opportunity. As technology continues to

evolve, artificial intelligence (AI) has emerged as a powerful tool in decoding the complexities of forex

trading. In this paper, we dig into the fascinating realm of AI in predicting forex market movements and

exchange rate fluctuations. People are becoming more and more active in currency trading these days.

While cryptocurrencies provide higher profits than foreign exchange, trading in the foreign exchange

(Forex) market is more reliable, secure, and regulated than cryptocurrency exchanges.

The foreign exchange market, commonly referred to as FOREX, is the largest in the world

(Levinson, 2014), with daily volume trades exceeding $5.1 trillion (Ozturk, Toroslu, & Fidan, 2016). Its

unknown nature and significant fluctuations in currency rates make it very volatile and complex,

frequently drawing comparisons to the black box (Anastasakis & Mort, 2009). In 1996, the first online

foreign currency trading platform was introduced, opening up the market to retail traders (Cartea,

Huang, & Masulis, 2019). Currency trading is available on the FOREX market around the clock (Masry,

Dupuis, Olsen, & Tsang, 2013), however, it is split into four main time zones (Wanjawa & Muchemi,

2014). These time zones are the Australian zone, Asian Zone, European Zone, and North American Zone.

Each of these zones has its opening hours and closing hours, which creates an arbitrage opportunity.

Its sophisticated web of geopolitical, economic, and psychological factors presents a dynamic

landscape where even the most professional traders find themselves fooled by uncertainty. The phrase

"share" or "stock price" refers to the price of shares, and a stock market is a marketplace for exchanging

stocks (equity) and other financial instruments of publicly traded firms (Ghaznavi et al., 2016). Stock
 2

market investments are frequently driven by forecasts of some kind [8]. Every day, billions of dollars are

exchanged on the stock market worldwide to turn a profit (Ticknor et al., 2013).

Nowadays, the number of methods that can be used to make predictions is increasing day by day,

as it has an important role to play in predicting future events. More sophisticated calculation models

have been developed and predictions are becoming more accurate as computers and technology advance

rapidly. Traditional methods of analysis often fall short of capturing the fine line and rapid fundamental

changes in currency markets. This is where AI steps in, the ability of a computer or robot controlled by

human beings to perform various actions that are similar to an intelligent creature. The ability to learn

from past experiences is the most important feature. Moreover, in recent times, it has been used widely in

the economy. It has been an important tool, especially for foreign exchange and gold foresight. Testing

whether using sophisticated algorithms and machine learning (ML) techniques combined with an

understanding of economic principles produces better forecasting outcomes than using estimates from

ordinary least squares (OLS) (Amat et al., 2018). To filter through vast amounts of data and uncover

patterns that may slip human analysis.

One of the key strengths of AI lies in its ability to adapt and learn from historical data,

continuously refining its predictive capabilities over time. By analyzing plenty

of factors including economic indicators, central bank policies, geopolitical events, and market Economic

behavior, AI models can identify trends and correlations that may influence commodities

movements. Moreover, AI systems can process information at speeds far surpassing human capacity,

enabling real-time analysis and decision-making in a market where every second counts.

This study aims to analyze the prices of Bitcoin and gold by employing both traditional and AI-

based methodologies, subsequently comparing their predictive accuracies with the actual market

outcome by examining traditional analyzing techniques alongside advanced AI methods, the research
 3

attempts to understand the accuracy of each approach in predicting the price movements of these two

marketable assets. Through rigorous analysis and comparison against real-world data, the study seeks to

highlight the strengths and limitations of both traditional and AI-driven prediction models in the context

of cryptocurrency and rich commodity markets.

This paper will answer the following questions:

1. Are AI methods more accurate in forecasting commodities and cryptocurrency prices

than the traditional method?

2. Which AI tool is more suitable to forecast the most accurate results?

2 -literature review

In this twenty-first century, the financial market is the pivot, and market economies and stock

prices determine the fate of every expanding economy, nation, or society (Nassirtoussi et al., 2014). Thus,

it is essential to study and learn about the financial market extensively. It's challenging to predict

financial markets because of a variety of uncertainties, including overall economic conditions, social

factors, and domestic and foreign political events (Adebiyi et al., 2012, 2014; Bisoi and Dash, 2014; Ding

et al., 2014; Rajashree et al., 2014; Rather et al., 2014; Lin, 2018). Like other financial variables, the

exchange rate is characterized by uncertainties, making the forecast of its parameters highly

unpredictable. In the financial sector, accurate predictions of important variables, such as the exchange

rate, have a huge influence on the global market and domestic economic policy formulation. The

assessment of the purchasing power of different currencies by both governments and businesses is based

on movements in exchange rates. Therefore, precise exchange rate modeling and forecasting are essential

for relevant trading and investment strategies (Baghestani & Toledo, 2019).
 4

There are two methods of predicting the market: fundamental and technical analysis.

Fundamental analysis considers many factors, such as the financial system and political state of a

country, the popularity of a company, and all internal and external buying and selling news. In contrast,

technical analysis focuses on predicting future prices based solely on historical data. Basic research,

technical analysis (charting), and technological methods (machine learning) are the three primary ways

for stock market predictions (Dunne, 2015). On the other hand, two categories are distinguished by some

academics: technical analysis and fundamental analysis (Nassirtoussi et al., 2014; Dunne, 2015; Gyan,

2015; Prem Sankar et al., 2015; Ahmadi et al., 2018). Analysts can enhance their overall valuation

estimate with the use of this information. Stock returns are predicted using both technical and

fundamental analysis, aiming to purchase stock at a discount to market value and sell it at a premium.

Despite being different in nature, both methods share the same goal: the evaluation of stock markets.

2.1 Technical analysis

Is one of the most popular methods for forex forecasting, and was first introduced by Charles

Dow and the Dow Theory in the late 1800s. In order to forecast future price changes, entails examining

historical pricing data and spotting patterns, trends, and other indicators. Making well-informed trading

decisions can help enhance the assessment of a security's strength or weakness in relation to the market

as a whole or one of its sectors. It is frequently used to produce short-term trading signals using various

charting tools.

(Vanstone & Finnie, 2009) brought to light the notion that some methods, including technical and

fundamental analysis, were created to forecast future price returns. Although technical analysis is widely

used by participants in many financial markets, as (Park & Irwin, 2009) note, academics have not

provided technical analysis with much support (Brock, Lakonishok, & LeBaron, 1992), despite the fact
 5

that it is readily available in financial markets, as (Schulmeister, 2009) has correctly pointed out.

Technical analysis, on the other hand, depends on previous stock price data (Chavarnakul & Enke, 2009).

According to some definitions, technical analysis is a collection of methods for estimating future returns

on financial assets through the examination of historical market data, primarily stock price, and volume

(Park & Irwin, 2007). Studies (Bisoi & Dash, 2014) have integrated statistical models, intelligent system

methodologies, and conventional technical analysis trading principles. Technical analysis is essentially a

set of guidelines or charting that attempts to predict future changes in prices by examining certain data,

such as the buying and selling prices as well as the volume of transactions, among other things (Gorgulho

et al., 2011). Investors who employ this strategy think that the share price takes in and reflects

information that has the power to influence the market (Murphy, 1999). Any security that has past

trading data can be subjected to technical analysis. This covers equities, futures, commodities, currencies,

fixed-income, and other assets.

Technical analysis is really significantly more common in FX and commodities markets since

traders there are more interested in short-term price changes. Although price fluctuations are the most

typical subject of technical analysis, some analysts also monitor other metrics like trade volume or open

interest statistics. Traders employ a variety of instruments and strategies, including oscillators, moving

averages, chart patterns, and Fibonacci retracements. Chart patterns like triangles, head and shoulders,

and double tops can give important information about impending market reversals or continuations.

While oscillators like the Relative Strength Index (RSI) and Stochastic Oscillators show overbought or

oversold circumstances, moving averages aid in trend identification and the determination of support

and resistance levels. Based on the Fibonacci sequence, Fibonacci retracements are used to determine

possible levels of support and resistance.

 6

Technical analysts use charts that show past market prices and technical indicators to try and

anticipate the direction of the stock market (Suresh-Kumar & Elango, 2011). (Filippou, Rapach, Taylor, &

Zhou, 2020) demonstrate that the currency market is predictable in terms of national traits, international

variables, and how they interact; this predictability results in substantial carry trading profits. The first

predictability evidence across bond rating for the corporate bond market is provided by (Guo, Lin, Wu, &

Zhou, 2020), along with a review of the literature. Technical analysis appears useful not only in the stock

market but also across asset classes. Technical analysis seems to be beneficial for many asset types.

However, the predictability is low and tends to decrease over time, much like it does in the stock market.

By examining historical and current stock price movements, a technical analyst can forecast the price of

stocks in the future (Anbalagan & Maheswari, 2014).

2.2 Fundamental Analysis

Based on a review of several Fundamental Analysis literature (Fontanilla & Gentile, 2001), The

concept of Fundamental Analysis, is "Knowledge of the rules and fixed steps access to its objectives of

determining the intrinsic value of shares in stock markets, through a general framework to study the

expected economic forecasts, leading to sectors which generate an increase in sales and profits, therefore

measure strength financial companies, the efficiency of management and business opportunities based

on historical financial statements and current conditions.

Generally speaking, there are two studies used to calculate share value: technical analysis and

fundamental security analysis (Hartono, 2007). Investors should analyze changes in share prices more

deeply by performing fundamental analysis based on financial ratios. By assessing the value of basic

elements that impact future stock prices and forecasting stock prices, fundamental analysis can be used

to estimate share prices (Husnan, 2009). Fundamental information is information related to the company
 7

condition in general, shown in financial statements that indicate company performance. These financial

statements can show some fundamental information such as financial ratios, cash flow, and other

performance measures associated with stock prices. Financial ratios can be classified into five categories:

Activity, Leverage, Liquidity, Profitability, and Valuation (Sutrisno, 2009). Through the analysis, the effect

of fundamental factors on stock prices and the correlation of these factors can be estimated.

Fundamental analysis involves analyzing economic and geopolitical factors that can influence the

value of a currency. Traders focus on factors such as interest rates, GDP growth, employment data,

inflation, central bank policies, and political stability. By understanding how these factors impact a

country’s economy, traders can make informed predictions about currency movements. For example, if a

country’s central bank raises interest rates, it may attract foreign investors, leading to an increase in the

value of its currency. On the other hand, political instability or weak economic data can cause a currency

to depreciate. Traders often follow economic calendars to stay updated on key economic events and news

releases that can impact currency movements.

Instead of focusing on the stock itself, fundamental analysts consider the firm that supports the

stock (Anbalagan & Maheswari, 2014). The data used by the fundamental analyst usually are

unstructured, which poses a difficult challenge. But infrequently, studies by (Zhang et al., 2011) have

shown it to be a reliable indicator of changes in stock prices. To forecast future stock prices, fundamental

analysis considers a variety of terrestrial and climatic factors, such as political data and natural or

unnatural disasters, as well as the firm's financial situation, board of directors, employees, and annual

report on the company's profits and losses (Tsai & Hsiao, 2010). Fundamental analysis, however, is not

appropriate for short-term stock-price change and is only helpful for long-term stock-price movement

(Khan, 2011). The fundamental analyst uses the openly accessible facts about the stock to perform an

analysis of stock price movement in three dimensions, concerning the economy, its industry, and the firm.
 8

They employed valuation models developed by Fundamental Analysts in the stock markets to

determine the fair (intrinsic) worth of the shares. These analysts assess the fair value of the firm based on

information about its past, present, and projected earnings (Bernard, 1994). It helps to discover

mispriced stocks (Kothari, 2001) and assigns intrinsic value to companies based on political and

economic facts, as well as historical and current financial records (Piotroski, 2000). Because the value of

the company is based on its ability to achieve cash flows and the uncertainty of those cash flows, the most

important principle of modern finance is that "any asset value equal to the present value of all expected

future cash flows discounted at the required return". Numerous strategies exist due to the intricacy and

significance of valuing common stock (Reilly & Brown, 2002). This type of analysis aids investors in

formulating investment plans that yield excess returns (Mahmoud & Sakr, 2012).

Also, the study (Chung & Kim, 2001) on the Hong Kong Stock Exchange sought to accomplish two

primary goals: The first involves creating a novel method to forecast equity's intrinsic value using

financial information from publicly available financial statements. The second objective is to predict the

stock's intrinsic value practically using the proposed model (which is achieved by objective one).

When creating successful basic investing strategies, fundamental elements like profitability,

solvency, liquidity, and operating efficiency are helpful. Additionally, there is a positive association

between these cumulative fundamental indicators and high-performing businesses. (Venkates, Madhu, &

Ganesh, 2012). (Nguyen, 2003) discovered that the three key components of fundamental analysis—cash

flows, outside funding, and dividends—can be used to both predict future stock returns and explain the

momentum phenomena in stock prices.

A mix of technical and fundamental analysis could be useful for predicting the prices of gold and

Bitcoin. In volatile markets like cryptocurrency markets, technical analysis can be useful in spotting

short-term trends and trading opportunities; on the other hand, fundamental research can offer valuable
 9

insights into the long-term drivers of value and performance of assets like gold. A more thorough grasp of

market dynamics and increased prediction accuracy may be obtained by combining aspects of both

strategies, depending on your investing goals, time horizon, and risk tolerance.

Due to the unstructured nature of fundamental factors, automation of fundamental analysis is

difficult. On the other hand, the emergence of machine learning has enabled researchers to automate

stock market prediction based on unstructured data, which in some cases has reported higher prediction

accuracy.

2.3 Artificial Intelligence

In terms of technological innovation, there have been three significant changes to the foreign

exchange market. The advent of electronic trading marked the first technological innovation in the

financial markets. The Internet followed in second place, and artificial intelligence (AI), which is primarily

utilized for exchange rate prediction, arrived third. Although the tests indicate that AI algorithms are

capable of producing precise short-term projections, they are also dependable in the long run. Long-term

forecasting is a challenge because it is more ambiguous. Future quotation modifications may be triggered

by new events or by the current events ceasing. Modern AI programs can be used to estimate currency

prices over a one-week period, provided that a set number of parameters remain constant.

AI supports the world's most actively traded markets by utilizing complex mathematical and

statistical models. In reality, artificial intelligence (AI) removes all geopolitical barriers and connects

disparate market segments, as demonstrated by the foreign currency market. AI is being used to facilitate

better communication amongst foreign exchange participants, including central banks, large commercial

banks, enterprises, and foreign exchange brokers. An important result of AI's application in foreign

exchange markets is that it makes the market more accessible, which raises market liquidity and, in turn,
 10

daily turnover. AI technology is used in machine learning, which enables computers to learn and develop

on their own without human assistance.

Recently, integrating machine learning (ML) techniques has become a powerful tool for

forecasting Forex trading. By using algorithms that are able to analyze large volumes of data, spot

patterns, and adjust to shifting market conditions, machine learning transforms the field of Forex

forecasting. ML models are capable of learning from historical data, making them well-suited for the non-

linear and complex nature of currency markets.

In Forex forecasting, deep learning models—especially neural networks—have become more

and more popular. In time series data, sequential dependencies can be effectively captured by Recurrent

Neural Networks (RNNs) and Long Short-Term Memory Networks (LSTMs). Predicting currency

movements can be facilitated by neural networks due to their ability to understand complex patterns and

relationships. it is well known that artificial neural networks (ANN) may predict stock market

movements using technical indicators in an abnormally profitable way (Fischer, T., & Krauss, C. 2018).

An artificial neural network (ANN) replicates the way the human brain learns by simulating the

brain's learning process. (Negnevitsky, M. 2005) They possess the ability to forecast and analyze. Using a

DL algorithm and blockchain data, (Senthuran, G., & Halgamuge, M. 2019) provided a way for projecting

cryptocurrency values. The ANN, as a DL technique, is used to recognize patterns or images by imitating

the visual processing of living organisms. CNNs are frequently employed to address issues with spatial

data, including picture data. Text and video analysis benefit more from the use of RNNs since they can

handle temporal and sequential data.

(Chandrinos, S. K., Sakkas, G., & Lagaros, N. D. 2018) proposed the Artificial Intelligence Risk

Management System (AIRMS) based on machine learning. AIRMS-ANN and AIRMS-DT, two risk

management structures that use neural networks and decision trees, respectively, were created. On
 11

average, both AIRMS-ANN and AIRMS-DT performed well, sometimes even surpassing one another. The

decision tree outperformed the neural network in terms of total return when the portfolios were

assessed using the Kelly criterion.

(Dash, R. 2018) proposed a model using a higher-order neural network forex prediction. To

forecast dynamic and nonlinear forex rates, they employed the Pi-Sigma neural network in conjunction

with a shuffling frog leap technique. (Ji, S., Kim, J., & Im, H. 2019) examined deep learning techniques for

Bitcoin price prediction, including deep neural networks (DNNs), convolutional neural networks (NNs),

and deep residual networks. They demonstrated that DNN-based models performed the best in

predicting Bitcoin price trends.

LSTM is a form of recurrent neural network (RNN) that learns long-term dependencies. provides

the opportunity to learn mapping functions between inputs and outputs and to directly handle order

across observations. Artificial Recurrent Neural Networks (ARNNs) in the domains of Deep Learning (DL)

and AI use LSTM. The approach is an ideal tool for financial asset price predictions since it can analyze

data sequences simultaneously and is helpful for classifying, analyzing, and producing forecasts on time

with serious data.

The ability of LSTMs to learn selectively by remembering and forgetting the necessary previous

data sets them apart from regular ANNs. By specifying a particular range of data for which the algorithm

is to make predictions and simultaneously determining the range and scope of data that the system

should ignore in order to prevent it from being destroyed by irrelevant data, this can be very helpful for

the financial assets trading system. An LSTM's advantage in financial price forecasting is its capacity to

forget data that the system designer determines is relevant and, thus, should be disregarded after a

certain amount of time in order to facilitate accurate predictions. Furthermore, (Ni, L., Li, Y., Wang, X.,
 12

Zhang, J., Yu, J., & Qi, C. 2019) suggested a model that employs the C-RNN technique to forecast Forex time

series. Convolutional and recurrent neural networks are used by C-RNN.

Sentiment is a process of determining the emotion behind a series of words whether that can be

attitudes, options, or emotions. The sentiments can be predicted by using the knowledge gained from

training datasets and using it to predict for testing datasets. Financial analysts have started using social

media more and more since it allows them to look at people's behavior in different situations rather than

simply raw facts. The idea is that “herd behavior” that exists in many life aspects also characterizes

investment behavior (Choijil et al., 2021), (Vo & Phan, 2018). Using a firm's sentiment on Twitter, (Tan &

Tas, 2020) examined the effects of social media on major international financial markets and discovered

a correlation between trading volume and returns and investor mood and Twitter activity. Using data

from Google Trends and Twitter, (Abraham et al., 2018) forecasted changes in the prices of Bitcoin and

Ethereum. They discovered that rather than tweet sentiment, tweet volume is a good indicator of price

direction.

Based on an extensive dataset of 84 million tweets and eight years' worth of stock data for 407

businesses from the S&P 500 index, (Liu et al., 2019) investigated whether social media had distinct

effects on stock performance. They discovered that whereas customers' negative opinion has a major

impact on stock prices, their good sentiment has little bearing on how well stocks perform. (Picasso et al.,

2019) created a prediction algorithm that can identify trends by combining technical analysis indicators

with investor sentiment gathered from news stories.(Wołk, 2020) contended that social media sentiment

and online search analytics tools like Google Trends play a major role in determining the volatility of

cryptocurrency prices. They also discovered that, despite declining cryptocurrency values, Twitter's

opinions are mostly optimistic.

 13

(Sohangir et al., 2018) applied a number of NN models to opinions expressed on the stock market

on Twitter and found that the convolutional neural network is the most effective model for predicting

sentiment from the dataset of stock tweets, while the deep learning model is useful for financial

sentiment analysis

(Kim et al., 2017) tried to predict Bitcoin’s trends by extracting keywords from Bitcoin-related

comments posted on online forums. However, misleading rumors and fake news have the power to

quickly change investors' emotions, therefore they should be carefully studied and can occasionally be

inaccurate.This is especially true for young or inexperienced investors who rely heavily on social media

to shape their personal views.

It is recommended that the system designer confirm investor sentiments from many sources

before incorporating them into the trading system in order to mitigate that occurrence while still using

social media as a source of information. In addition to doing real trading and producing precise forecasts,

algorithms can also provide a range of back-testing outcomes that may be suitable for different investor

risk tolerance levels. AI tools can gather information from various sources from financial exchanges,

global economies, and social media.

Pattern recognition and breakout signaling are two other significant ways that AI is advancing

trading. The system is configured to identify established patterns in this field of expertise and determine

when to enter or exit a trade based on those patterns. Time series prediction has also made use of natural

language processing (Nassirtoussi et al., 2014; Basha et al., 2017).

ML methods that make use of data analysis are effective for Forex forecasting. Fundamental and

technical analyses are frequently used in traditional Forex forecasting techniques. Exchange rate

fluctuations can be caused by a variety of circumstances. These elements are qualitative as well as

quantitative, so while some can be easily modeled, others may be challenging to measure. Normally, AI
 14

gadgets would enable investors to simulate both qualitative and quantitative aspects. Numerical

measurements can be made of quantitative factors that result from both macroeconomic and

microeconomic shifts. Comparatively speaking, qualitative characteristics are harder to quantify, yet they

nevertheless affect quotations. The combination of neural networks with expert systems has improved

prediction accuracy and performance. (Alexandridis et al., 2018; Yu, 2005; Nedovic, 2002; Guimaraes,

1994).

Compared to equities, the forex market is one of the most complex due to its high volatility,

nonlinearity, and irregularity (Ahmed et al., 2020). The Bitcoin exchange is more sensitive to economic

fundamentals and less susceptible to technological problems. The c-RNN version has much fewer errors

(calculated by RMSE) than LSTM and CNN.

Methodology-3

Based on the comparison provided, determining the "best" method for market analysis depends

on various factors, including the trader's goals, time horizon, and expertise level. Technical analysis,

focusing on historical price data and chart patterns, is particularly effective for short-term trading due to

its immediate trading signals and ability to identify trends and market reversals. However, its predictive

power may decrease over time, and it does not account for broader economic or company-specific

factors.

On the other hand, fundamental analysis, centered around the intrinsic value of assets based on

economic indicators and company performance, is more suitable for long-term investment decisions. It

provides a deep understanding of underlying asset value and is useful for identifying mispriced securities

and long-term growth potential. Nonetheless, its reliance on complex and unstructured data makes it less

effective for short-term price movements.

 15

Machine learning and AI techniques offer a promising approach to market analysis by automating

and enhancing prediction models using both structured and unstructured data. These methods, such as

neural networks and decision trees, demonstrate high predictive accuracy, especially in handling

complex and nonlinear data. However, they require significant computational resources and expertise,

and their opaque nature can make interpretation challenging.

Contribution-4

The introduction sets the stage for exploring the role of artificial intelligence (AI) in predicting

movements in foreign exchange (forex) markets. It portrays the forex market as a complex and volatile

environment where predicting fluctuations is both challenging and rewarding. By contrasting forex

trading with cryptocurrency exchanges, the introduction emphasizes the reliability, security, and

regulation of forex trading. The significance of the forex market, with its massive daily trading volume, is

highlighted, along with its divided trading hours across major time zones. Furthermore, the introduction

underscores the challenges posed by geopolitical, economic, and psychological factors in forex trading. It

also introduces the relevance of AI in overcoming these challenges, leveraging its ability to analyze vast

amounts of data, learn from historical patterns, and adapt to changing market conditions. The paper's

objective to analyze the accuracy of AI-based methodologies in predicting commodity and

cryptocurrency prices compared to traditional methods is outlined, setting the research agenda for the

subsequent sections. Finally, it presents key questions the study aims to address, focusing on the

comparative effectiveness of AI methods and traditional approaches in forecasting market movements.

 16

5-Conclusion

In-depth discussion of forex trading and artificial intelligence's (AI) capacity to forecast market

movements is provided in this article. It talks about the difficulties caused by geopolitical, economic, and

psychological variables as well as the complexities of the foreign exchange market and how reliable it is

in comparison to cryptocurrency exchanges. The study emphasizes AI-driven methods as effective means

of enhancing prediction accuracy and evaluating enormous volumes of data. In predicting commodities

and cryptocurrency values, it contrasts conventional and AI-based approaches and comes to the

conclusion that AI techniques have potential to improve prediction accuracy, particularly in volatile

markets like cryptocurrencies. The use of artificial intelligence (AI) technologies into forex forecasting is

considered a noteworthy progression, providing traders with unparalleled perspectives and prospects

for well-informed decision-making.

 17

References

1. Levinson, M. (2014). The Economist Guide to Financial Markets: Why They Exist and How They Work.
London, UK: The Economist.

2. Ozturk, M., Toroslu, I. H., & Fidan, G. (2016). Heuristic based trading system on Forex data using technical
indicator rules. Applied Soft Computing, 43, 170–186.

3. Anastasakis, L., & Mort, N. (2009). Exchange rate forecasting using a combined parametric and
nonparametric self-organizing modeling approach. Expert Systems with Applications, 36, 12001–12011.

4. Cartea, A., Huang, R. D., & Masulis, R. W. (2019). FX spreads and dealer competition across the 24-h
trading day. Review of Financial Studies, 12, 61–93.

5. Masry, S., Dupuis, A., Olsen, R., & Tsang, E. (2013). Time zone normalization of FX seasonality.
Quantitative Finance, 13, 1115–1123.

6. Wanjawa, B. W., & Muchemi, L. (2014). ANN Model to Predict Stock Prices at Stock Exchange Markets.

7. Ghaznavi, A., Aliyari, M., & Mohammadi, M. R. (2016). Predicting stock price changes of Tehran artmis
company using radial basis function neural networks. International Research Journal of Applied Basic Sciences,
10(8), 972–978.

8. (Ticknor, 2013; Chen et al., 2014; Metghalchi et al., 2014; Rather et al., 2014; Prem Sankar et al., 2015;
Wanjawa, 2016; Agarwal et al., 2017; Tsai & Wang, 2017; Lin, 2018; Zhou et al., 2018).

9. Amat, Christophe, Michalski, T., & Stoltz, G. (2018). Fundamentals and exchange rate forecastability with
simple machine learning methods. Journal of International Money and Finance, 88, 1–24.

10. Nassirtoussi, A. K., Aghabozorgi, S., Wah, T. Y., & Ngo, D. C. L. (2014). Text mining for market
prediction: A systematic review. Expert Systems with Applications, 41, 7653–7670.

11. Adebiyi et al. (2012, 2014); Bisoi and Dash (2014); Ding et al. (2014); Rajashree et al. (2014); Rather et al.
(2014); Lin (2018).

12. Baghestani, H., & Toledo, H. (2019). Oil prices and real exchange rates in the NAFTA region. The North
American Journal of Economics and Finance, 48, 253-264.

13. Vanstone, B., & Finnie, G. (2009). An empirical methodology for developing stockmarket trading systems
using artificial neural networks. Expert Systems with Applications, 36(3), 6668-6680.

14. Murphy, J. J. (1999). Technical Analysis of the Financial Markets: A Comprehensive Guide to Trading
Methods and Applications. New York, NY, USA: New York Institute of Finance.

15. (Suresh- Kumar and Elango, 2011; Wei et al., 2011; Suthar et al., 2012; de Oliveira et al., 2013; Ballings et
al., 2015; Gaius, 2015; Su and Cheng, 2016).
 18

16. Filippou, I., Rapach, D., Taylor, M. P., & Zhou, G. (2020, September 10). Exchange Rate Prediction with
Machine Learning and a Smart Carry Portfolio.

17. Guo, X., Lin, H., Wu, C., & Zhou, G. (2020, December 2). Extracting Information from Corporate Bond
Yields: A Machine Learning Approach.

18. Fontanills, A. G., & Gentile, T. (2001). The Stock Market Course. John Wiley & Sons, Inc.

19. (Bernard, 1994; Fischer and Jordan, 1995; Penman, 1991; Bauman, 1996; Rielly and Brown, 2002; Jones,
2007; Bodie et al., 2009).

20. Reilly, F., & Brown, K. (2002). Investment Analysis and Portfolio Management (7th Ed.). South-Western.

21. Chung, H. Y., & Kim, J. B. (2001). A structured financial statement analysis and the direct prediction of
stock prices in Korea. Asia Pacific Financial Markets, 8(2), 87-117. Venkates, R., Madhu, S. C., & Ganesh, L.
S. (2012).

22. Brock, W. A., Lakonishok, J., & LeBaron, B. (1992). Simple technical trading rules and the stochastic
properties of stock returns. Journal of Finance, 47, 1731–1764.

23. Nguyen, P. (2003). Fundamental analysis and stock returns: Japan 1993-2003. Tokyo: WBP Financial
Integrator.

24. Ball, R., Kothari, S. P., & Watts, R. L. (1993). Economic determinants of the relation between earnings
changes and stock returns. The Accounting Review, 68(3), 622-638.

25. Piotroski, J. (2002). Value investing: The use of historical financial statement information to separate
winners from losers. Journal of Accounting Research.

26. Chavarnakul, T., & Enke, D. (2009). Parisi & Vasquez, & Roberts. In Journal Title (p. 3517).

27. Mahmoud, A., & Sakr, S. (2012). The predictive power of fundamental analysis in terms of stock return and
future profitability performance. International Research Journal of Finance and Economics.

28. Chung, H. Y., & Kim, J. B. (2001). A structured financial statement analysis and the direct prediction of
stock prices in Korea. Asia-Pacific Financial Markets, 8, 87–117.

29. Reilly, F., & Brown, K. (2002). Investment Analysis and Portfolio Management (7th ed.). South-Western.

30. Bernard, V. L. (1994). Accounting-based valuation methods, determinants of market-to-book ratios, and
implications for financial statements analysis (Working paper No. 9401). University of Michigan, Business
School, Faculty Research.