Forecasting Directional Movement Of Forex Data Using Lstm With Technical And Macroeconomic Indicators - Alpha Dent Implants

# Forecasting Directional Movement Of Forex Data Using Lstm With Technical And Macroeconomic Indicators

Our proposed hybrid model, which combines two separate LSTMs corresponding to these two data sets, was found to be quite successful in experiments using real data. In this work, we propose a hybrid model composed of a macroeconomic LSTM model and a technical LSTM model, named after the types of data they use. We first separately investigated the effects of these data on directional index options movement. After that, we combined the results to significantly improve prediction accuracy. The macroeconomic LSTM model utilizes several financial factors, including interest rates, Federal Reserve funds rate, inflation rates, Standard and Poor’s (S&P) 500, and Deutscher Aktien IndeX market indexes. Each factor has important effects on the trend of the EUR/USD currency pair.

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 forex forecast and the traders profit if the prediction of the direction is correct. The data set was created with values from the period January 2013–January 2018.

The coefficients a, b, and c will determine how much a certain factor affects the exchange rate and direction of the effect . This method is probably the most complex and time-consuming approach, but once the model is built, new data can be easily acquired and plugged in to generate quick forecasts. Purchasing power parity looks at the prices of goods in different countries and is one of the more widely used methods for forecasting exchange rates due to its indoctrination in textbooks. In Eq.26, SMA is the simple moving average, Close is the closing price of the currency pair, N is the period, and SUM is the sum of closing prices in period N.

## Forecast Tables And Statistics

The foreign exchange market, known as Forex or FX, is a financial market where currencies are bought and sold simultaneously. Forex is the world’s largest financial market, with a volume of more than \$5 trillion. It is a decentralized market that operates 24 h a day, except for weekends, which makes it quite different from other financial markets. After the preprocessing stage, the TI_LSTM model is trained using these seven technical indicators together with the closing values of the EUR/USD pair.

When playing Plinko3 a flat disk is released from the top of a flat wooden board. As the disk descends, its fall is interrupted by pegs which alter its direction left or right. Where the disk finally comes to rest is virtually impossible https://ngcservices.co/umarkets-review-2021/ to predict. Currencies can move from period to period as randomly as the Plinko disk moves from row to row. Contact Us Let SVB experts help your business with the right mix of products, services and strategic advice.

Notably, of the 56 guesses, only one guess beat the group average estimate. Strategize with our financial experts to help you achieve your business goals. “An uptick in growth number could keep the rupee supported at lower levels… We expect the dollar would continue to strengthen against its major crosses and that could weigh on the rupee as well.

Kara et al. compared the performance of ANN and SVM for predicting the direction of stock price index movement. They found that ANN, with an accuracy of 75.74%, performed significantly better than SVM, which had an accuracy of 71.52%. 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.

• CCI is based on the principle that current prices should be examined based on recent past prices, not those in the distant past, to avoid confusing present patterns .
• Additionally, the average predicted transaction number is 206.25, corresponding to 85.23% of the test data.
• With that simulator, he managed to make profit in all six stock domains with an average of 6.89%.
• Huang et al. examined forecasting weekly stock market movement direction using SVM.

N is the period, SMA is the simple moving average, MeanDeviation is the mean deviation, and L is the Lambert coefficient, equal to 0.015. N is the period, and Close and Close are the closing price and closing price N periods ago, respectively. To further validate our results, we extended our data set to include a very recent one—namely, EUR/USD rates from January 1, 2018, to April 1, 2019. This extended data set has 1539 data points, which contain 761 increases and 777 decreases overall.

## What Is The Name Of The Currency In New Zealand?

The other model is the technical LSTM model, which takes advantage of technical analysis. Technical analysis is based on technical indicators that are mathematical functions used to predict future price action. In “Related work” section, related studies of the financial time-series prediction problem are thoroughly examined. “Forex preliminaries”–“Technical indicators” sections provide background information about Forex, LSTM, and the technical indicators.

We can also conclude that as the number of transactions increased, it reduced the accuracy of the model. This was an expected result, and it was observed in all of the experiments. Depending on the data set, the number of transactions generated by our model could vary. After applying the labeling algorithm, we obtained a balanced distribution of the three classes over the data set. This algorithm calculates different threshold values for each period and forms different sets of class distributions.

The average predicted transaction number is 157.25, which corresponds to 64.71% of the test data. For this test case, the accuracy significantly increased, but the number of transactions dropped even more significantly. 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.

Gold reversed its direction after climbing to multi-week highs above \$1,870. XAU/USD could come under renewed bearish pressure if \$1,850 support fails. Markets are expected to turn quiet after high-tier data releases from the US on Wednesday. The solid black line represents the actual FX rate (“spot rate”), and the lighter black vertical lines represent the size of the forecasting error . In his book Wisdom of the Crowd, James Surowiecki writes that the collective opinion of a group is often superior to that of any one individual in the group. He supports this conclusion with examples including the jelly-beans-in-the-jar experiment in which 56 people were asked to guess the number of jelly beans in a jar that held 850 beans.

## Foreign Currency Exchange Rate Prediction Using Neuro

Similar to the technical LSTM model, the profit_accuracy results are close to each other, except at 200 iterations, with an overall average accuracy of 48.73% ± 8.49%. Meanwhile, the average predicted transaction number is 138.75, corresponding to 57.34% of the test data. However, the case of 200 iterations is not an exception, and there is huge variance among the cases. A technical indicator is a time series that is obtained from mathematical formula applied to another time series, which is typically a price .

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. Guresen et al. explored several ANN models for predicting stock market indexes. These models include multilayer perceptron , dynamic artificial neural network , and hybrid neural networks with generalized autoregressive conditional heteroscedasticity . Applying mean-square error and mean absolute deviation , their results showed that MLP performed slightly better than DAN2 and GARCH-MLP while GARCH-DAN2 had the worst results. Moreover, the average profit_accuracy values are 71.24% ± 5.40% and 68.25% ± 4.95% for the ME_LSTM- and TI_LSTM-based modified hybrid models, respectively. According to the results, profit_accuracy had high variance, with 51.31% ± 7.83% accuracy on average.

The average predicted transaction number is 151.50, corresponding to 62.60% of the test data. Again, the case of 200 iterations shows huge differences from the other cases, generating less than half the number of the lowest number of transactions generated by the others. As shown in Table9, in this set of experiments, the profit_accuracy results showed smaller variance, with 48.58% ± 3.95% on average. Furthermore, the variance in the number of transactions is also smaller; the average predicted transaction number is 146.50, which corresponds to 60.29% of the test data. There is a drop in the number of transactions for 200 iterations but not as much as with the macroeconomic LSTM. The profit_accuracy results have higher variance, with 53.05% ± 7.42% accuracy on average.

AverageGain, AverageLoss, AverageGain, and AverageLoss are the previous period’s average gain and loss and the current average gain and loss in N periods, respectively. In future research, our work could be extended to other currency pairs, such as EUR/GBP, GBP/USD, USD/CHF, GBP/CHF, and EUR/CHF. Additionally, a trading simulator could be developed to further validate the model. Such a simulator could be useful for observing the real-time behavior of our model.

When the ME_LSTM and TI_LSTM were executed separately using the features of their corresponding data sets (i.e., macroeconomic features and technical indicator features), they generated too many transactions. Some of stock exchange these transactions were generated with not very good signals and thus had lower accuracy results. When all features were simply appended to each other, in what we call ME_TI_LSTM, the results did not change much.

July 2, 2020
Share

## Other articles

Stay in touch with us.
Current Information from Alpha Dent Implants