Forecasting directional movement of Forex data using LSTM with technical and macroeconomic indicators

In particular, LSTM models seem to improve the accuracy of volatility forecasts. Additionally, Ramos-Pérez et al. predicted S&P 500 index volatility using a stacked ANN model based on a set of various machine learning techniques, including gradient descent boosting, RF, and SVM. They demonstrated that volatility forecasts can be improved by stacking machine learning algorithms. Additionally, regardless of the volatility model adopted, high-volatility regimes lead to higher error rates. Forex is a special financial market that entails both high risks and high profit opportunities for traders. It is also a very simple market since traders can profit by just predicting the direction of the exchange rate between two currencies.

Additionally, because fluctuations in FX affect the value of imported and exported goods and services, such fluctuations have an important impact on the economic competitiveness of multinational corporations and countries. Therefore, the volatility of FX rates is a major concern for scholars and practitioners. Forecasting FX volatility is a crucial financial problem that is attracting significant attention local businesses hiring near me based on its diverse implications. Recently, various deep learning models based on artificial neural networks have been widely employed in finance and economics, particularly for forecasting volatility. The main goal of this study was to predict FX volatility effectively using ANN models. To this end, we propose a hybrid model that combines the long short-term memory and autoencoder models.

CFD, share dealing and stocks and shares ISA accounts provided by IG Markets Ltd, spread betting provided by IG Index Ltd. Registered address at Cannon Bridge House, 25 Dowgate Hill, London EC4R 2YA. Both IG Markets Ltd and IG Index Ltd are authorised and regulated by the Financial Conduct Authority. 79% of retail investor accounts lose money when trading spread bets and CFDs with this provider.

The PPP forecasting approach is based on the theoretical law of one price, which states that identical goods in different countries should have identical prices. Now, using this model, the variables mentioned, i.e., INT, GDP, and IGR can be used to generate a forecast. The coefficients used will affect the exchange rate and will determine its direction . The second period represents the time around Brexit, which caused fluctuations in the global stock market, particularly in the European market.

Gross domestic product is the monetary value of all finished goods and services made within a country during a specific period. The offers that appear in this table are from partnerships from which Investopedia receives compensation.

This extension significantly reduced the number of transactions, by mostly preventing risky ones. As can be seen in Table20, which summarizes all of the results, the new approach predicted fewer transactions than the other models. Moreover, the accuracy of the proposed transactions of the hybrid approach is much higher than that of the other models. In the one-day-ahead predictions, the individual LSTM models had a slightly better profit_accuracy than ME_TI_LSTM, which was less than 1%. However, they produced 3.91% fewer transactions than ME_TI_LSTM on average. Moreover, when we combined the predictions of the individual models in our proposed model, it reached a much higher profit_accuracy of 73.09% (22.30% improvement) on average while reducing the number of transactions to 37.96%.

forecasting forex

The relative economic strength model determines the direction of exchange rates by taking into consideration the strength of economic growth in different countries. The idea behind this approach is that a strong economic growth will attract more investments from foreign investors. To purchase these investments in a particular country, the investor will buy the country’s currency – increasing the demand and price of the currency of that particular country. Several studies have proposed hybrid models based on GARCH-based models and ANN models. Additionally, some studies have proposed hybrids of LSTM and GARCH models and have used such models to predict the volatility of financial assets (Kim and Won and Hu et al. ). According to empirical results, hybrid models based on GARCH and ANN techniques exhibit improved forecasting performance in terms of volatility accuracy.

Using fundamental analysis to predict forex movements

They compared their model with a baseline consisting of multilayer perceptron, random forest, and pseudo-random models. They concluded that LSTM performed significantly better than the baseline models, according to the Kruskal–Wallis test. As the name may suggest, the relative economic strength approach looks at the strength of economic growth in different countries in order to forecast the direction of exchange rates. The rationale behind this approach is based on the idea that a strong economic environment and potentially high growth are more likely to attract investments from foreign investors.

Chart analysis and price analysis using technical indicators are the two main approaches in technical analysis. While the former is used to detect patterns in price charts, the latter is used to predict future price actions (Ozorhan et al. 2017). Fundamental analysis and technical analysis are the two techniques commonly used for predicting forex fundamentals future prices in Forex. While the first is based on economic factors, the latter is related to price actions . Selvamuthu et al. used neural networks based on Levenberg–Marquardt, scaled conjugate gradient, and Bayesian regularization for stock market prediction based on tick data and 15-min-interval data for an Indian company.

What is forecasting in forex?

Forecasting in FX means predicting current and future market trends by utilising existing data and various facts. Being an analyst, one should rely on both fundamental and technical statistics in order to predict the directions of the economy, the stock market, and individual securities.

DAX is the German stock index, which has a strong relationship on the price of the EUR while the S&P 500 is one a US stock index that affects the USD. Central banks’ interest rates are also important factors determining the prices of currencies. Therefore, the interest rates determined by the Central Bank of Europe and the Fed directly affect EUR and USD prices, respectively. Hu et al. introduced an improved sine–cosine algorithm for optimizing the weights and biases of BPNN to predict the directions of open stock prices of the S&P 500 and Dow Jones Industrial Average indices.

This paper aims to compare different trading systems based on support vector regression, growing hierarchical self-organizing maps and genetic algorithms when tested against nine currency pairs of the foreign exchange market . The autoencoder, which was first introduced in , utilizes a neural network consisting of an input layer, output layer, and hidden layers for self-supervised learning. Although this structure is similar to that of a typical neural network, the output and input layers have isomorphic vectors. The goal of this model is to derive a representation for an input dataset (e.g., dimensionality reduction) and make the reorganized data as close as possible to the input data. As shown in Figure 6, the encoder represents a stage at which the model can learn important characteristics of inputs and the decoder forms outputs similar to the inputs. The output represents a state in which the noise of the inputs is removed, resulting in more distinct characteristics.

Baseline LSTMs

Many investors did this with the Japanese yen when the interest rates in Japan were at extreme lows. The goal is to simulate the judgment and decision making of the human expert with a system that responds in a timely manner to changes in market conditions, thus allowing the optimization of ultra-short-term transactions. Monex USA also ranked for several of the individual currencies in addition to the G10 accolades. Our award-winning FX forecasters are laser-focused on helping companies navigate the volatile currency market efficiently and cost effectively.

Our hybrid model utilizes an LSTM model as an encoder and decoder inside an autoencoder network. Additionally, we investigate FXVIX indices through subperiod analysis to examine how the proposed model’s forecasting performance is influenced by data distributions and outliers. Based on the empirical results, we can conclude that the proposed hybrid method, which we call the autoencoder-LSTM model, outperforms the traditional LSTM method. Additionally, the ability to learn the magnitude of data spread and singularities determines the accuracy of predictions made using deep learning models. In summary, this study established that FX volatility can be accurately predicted using a combination of deep learning models. Because forecasting volatility is an essential task for financial decision-making, this study will enable traders and policymakers to hedge or invest efficiently and make policy decisions based on volatility forecasting.

A novel hybrid model is proposed that combines two different models with smart decision rules to increase decision accuracy by eliminating transactions with weaker confidence. Both macroeconomic and technical indicators are used as features to make predictions. The goal is to automate identification of technical indicators or chart patterns across a range of currency pairs in order to identify trade entry and exit points.

Fortunately for forex traders there is an easy way to keep up with developments and prepare for the major events that move the price of currencies, the ones that are scheduled anyway. An economic calendar is crucial for anybody trading forex and a guide to the biggest economic and political events that are likely to have an effect, one way or another, on forex and other financial markets. Not all types of forex trading are proactive, whereby traders predict where they believe a certain currency to be heading, but reactive, responding to moves in price. Range trading is mainly used for currencies that roam up and down in price but have no clear long-term trend. Foreign exchange, more commonly known as forex, is the most traded market in the world. Well over $5 trillion of currency is traded in a single day, dwarfing the hundreds of billions traded on stock markets around the world.

Forecasting Forex Trading

Based on these features, autoencoders are mainly used for image restoration or noise reduction. However, when a cross-validation method that selects random samples (e.g., K-fold cross-validation) is applied to time-series data, past values are predicted using future values. Therefore, in this study, time-series nested cross-validation was adopted to maintain the temporal order of the dataset for gradual overlapping and learning. The proposed model was trained and tuned on training and validation sets in each fold and then evaluated on a testing set.

The profit_accuracy results are very close to each other, except at 200 iterations, with 53.84% ± 21.25% accuracy on average. Additionally, the average predicted transaction number is 158.50, which corresponds to 65.23% of the test data. However, the case with 200 iterations is quite different from the others, with only 10 transactions out of a possible 243 generating a very high profit accuracy. This LSTM model was formed using all of the macroeconomic and technical indicators taken together to observe the effects of the combined set of indicators. After the preprocessing stage, ME_TI_LSTM was trained using the macroeconomic and technical indicators mentioned above together with the closing values of the EUR/USD currency pair. Similarly, Di Persio and Honchar applied LSTM and two other traditional neural network based machine learning tools to future price prediction.

forecasting forex

This is because a split is made between the training and test sets without shuffling the data sets to preserve the order of the data points. If the predictions of the two models are different, we choose for the final decision the one whose prediction has higher probability. If the probability is the same, we choose the prediction of the TI_LSTM model. The data set was split into the training and test sets, with ratios of 80% and 20%, respectively.

Using technical analysis to predict forex

The data used to support the findings of this study are available from the corresponding author upon request. We used a grid search to identify and apply optimal parameters for each section of our model. The optimized parameters are the batch size, activation function, and optimizer function. CFDs are leveraged products and as such loses may be more than the initial invested capital. Trading in CFDs carry a high level of risk thus may not be appropriate for all investors. The data is easily available and is 99.9% the same for everyone, resulting in an objective approach.

forecasting forex

In a real Forex trading system, there are further important considerations. For example, closing the transaction can be done based on additional events, such as the occurrence of a stop-loss, take-profit, or reverse signal. Another important consideration could be related to account management. The amount of the account to be invested at each transaction could vary. The simplest model might invest the whole remaining account at each transaction. However, this approach is risky, and there are different models for account management, such as always investing a fixed percentage at each transaction.

If one of these is predicted, a transaction is considered to be started on the test day ending on the day of the prediction . A transaction is successful and the traders profit if the prediction of the direction is correct. Stop loss is an order to sell a currency bollinger band calculations when it reaches a specified price. Take profit is an order by the trader to close the open position for a gain when the price reaches a predefined value. This order guarantees profit for the trader without having to worry about changes in the market price.

This allowed errors to be averaged to obtain an unbiased error estimate (Varma and Simon ). In short-term forecasting, models with higher attention to technical analysis tend to prevail — mostly, because both fundamental and sentiment analysis cannot provide enough reliable information at low enough resolution. Retail — some retail Forex brokers provide information on how their traders are positioned on a given currency pair. This information is very basic of course — usually, it is just a percentage of long and short positions, long and short orders, and sometimes, concentration of those orders at specific exchange rate levels. Additionally, retail FX sentiment may be glimpsed from trade sharing websites such as Myfxbook and ForexFactory. When trying to determine the future exchange rate between two currencies, the economist also must understand economic fundamentals in both nations, according to IG.

Because FX risk is directly linked to transaction costs related to international trade, it is of great importance for multinational firms, financial institutions, and traders who wish to hedge currency risks. In this regard, FX volatility has affected the external sector competitiveness of international trade and the global economy. Sadly, you would have to wait a rather long time to profit from a long-term forecast. That is why most Forex traders are attracted to short-term FX forecasting and cope with its lower average accuracy.

Zhang et al. proposed a state-frequency memory recurrent network, which is a modification of LSTM, to forecast stock prices. By decomposing the hidden states of memory cells into multiple frequency components, they could learn the trading patterns of those frequencies. They used state-frequency components to predict future price values through nonlinear regression. They used stock prices from several sectors and performed experiments to make forecasts for 1, 3, and 5 days.

Machine Learning Applications in Complex Economics and Financial Networks

There has been a great deal of work on predicting future values in stock markets using various machine learning methods. The main decision in Forex involves forecasting the directional movement between two currencies. Traders can profit from transactions with correct directional prediction and lose with incorrect prediction.

Can machine learning predict forex?

The exchange rate of each money pair can be predicted by using machine learning algorithm during classification process. With the help of supervised machine learning model, the predicted uptrend or downtrend of FoRex rate might help traders to have right decision on FoRex transactions.

For long-term forecasting, fundamental analysis offers plenty of macroeconomic indicators. In fact, most of them aren’t available in a higher resolution than monthly. This method of using three currencies to calculate the expected exchange rate between two of those three currencies is called triangulation.

We showed that rather than combining these parameters into a single LSTM, processing them separately with different LSTMs and combining their results using smart decision logic improved prediction accuracy significantly. In most financial markets, accurate predictions above 50% technically generate profits. Considering other costs and risks, we can conclude that more than 60% prediction accuracy is a very successful result, and we showed that our hybrid model always had an accuracy of greater than 60%.

First, the spread of data and presence of outliers increase the accuracy of forecasting performance of the proposed model. Second, improvements in prediction accuracy are more pronounced with autoencoder-LSTM than with LSTM. Finally, for predicting FXVIXs, the autoencoder-LSTM model is superior to the LSTM. Data-driven methods are more powerful than model-driven methods for forecasting asset price time-series data (see Kim et al. ). In this study, we investigated how event-driven data, which focus on events such as outliers in data-driven analysis, contribute to model performance.

As shown in Figure 7, this model has a structure similar to that of a typical autoencoder, but it takes input data with added noise as new input data. Predicting what direction exchange rates are heading by painting a picture of the overall health of an economy is called the relative economic strength approach. This doesn’t forecast what the exchange rate should be, but allows traders to decide whether they think it is heading higher or lower.

Leave a Comment

Your email address will not be published. Required fields are marked *