재무 예측은 금융 시스템의 본질적인 복잡성으로 인해 어려운 작업입니다. 예측의 단순화된 접근 방식은 경제 구조에 대해 거의 가정하지 않는 신경망과 같은 "블랙 박스" 방법으로 제공됩니다. 본 논문에서 우리는 신경망을 금융 시계열 예측 방법으로 사용한 경험을 관련시킵니다. 특히 50%를 약간 넘는 성공률로 가격 상승의 신호를 예측할 수 있는 신경망을 찾을 수 있음을 보여줍니다. 목표 시리즈는 약 1990년 1월부터 2000년 2월까지의 기간 동안 다양한 자산 및 지수의 일일 종가입니다.
우리는 NARX 신경망과 시간 이동 배깅 기법 및 상대 강도 지수 및 확률적 지표와 같은 재무 지표를 기반으로 Forex 시장의 움직임을 예측하는 새로운 방법을 제안합니다. 신경망은 뛰어난 학습 능력을 가지고 있지만 잡음이 있는 데이터에 대해 좋지 않고 예측할 수 없는 성능을 보이는 경우가 많습니다. 정적 신경망과 비교할 때 우리의 방법은 응답의 오류율을 크게 줄이고 예측 성능을 향상시킵니다. 응답을 예측하기 위해 세 가지 유형의 아키텍처를 테스트하고 최상의 네트워크 접근 방식을 결정했습니다. 우리는 시간당 환율을 예측하기 위해 우리의 방법을 적용했고 두 가지 다른 환율(GBPUSD 및 EURUSD)에 대한 포괄적인 실험에서 놀라운 예측 가능성을 발견했습니다.
높은 정확도에도 불구하고 신경망은 입력에 대한 작은 섭동으로 인해 레이블이 잘못 지정될 수 있는 적대적 예에 민감한 것으로 나타났습니다. 우리는 신경망의 견고성을 측정하기 위한 메트릭을 제안하고 선형 프로그램으로 견고성의 인코딩을 기반으로 이러한 메트릭을 근사화하기 위한 새로운 알고리즘을 고안합니다. MNIST 및 CIFAR-10 데이터 세트에 대한 실험을 통해 메트릭을 사용하여 심층 신경망의 견고성을 평가하는 방법을 보여줍니다. 우리의 알고리즘은 기존 알고리즘을 기반으로 한 추정치에 비해 견고성 메트릭에 대한 더 유익한 추정치를 생성합니다. 또한 특정 알고리즘을 사용하여 생성된 적대적 예제에 대해 견고성을 "과적합"하는 기존 접근 방식을 보여줍니다. 마지막으로, 우리는 우리가 제안하는 메트릭뿐만 아니라 이전에 제안된 메트릭에 따라 신경망 견고성을 추가로 개선하는 데 우리 기술을 사용할 수 있음을 보여줍니다.
The Foreign Exchange Market is the biggest and one of the most liquid markets in the world. This market has always been one of the most challenging markets as far as short term prediction is concerned. Due to the chaotic, noisy, and non-stationary nature of the data, the majority of the research has been focused on daily, weekly, or even monthly prediction. The literature review revealed that there is a gap for intra-day market prediction. Identifying this gap, this paper introduces a prediction and decision making model based on Artificial Neural Networks (ANN) and Genetic Algorithms. The dataset utilized for this research comprises of 70 weeks of past currency rates of the 3 most traded currency pairs: GBP\USD, EUR\GBP, and EUR\USD. The initial statistical tests confirmed with a significance of more than 95% that the daily FOREX currency rates time series are not randomly distributed. Another important result is that the proposed model achieved 72.5% prediction accuracy. Furthermore, implementing the optimal trading strategy, this model produced 23.3% Annualized Net Return.
In this paper we investigate and design the neural networks model for FOREX prediction based on the historical data movement of USD/EUR exchange rates. Unlike many other techniques of technical analysis which are based on price trends analysis, neural networks offer autocorrelation analysis and the estimation of possible errors in forecasting. This theory is consistent with the semi-strong form of the efficient markets hypothesis. The empirical data used in the model of neural networks are related to the exchange rate USD/EUR in the period 23.04.2012–04.05.2012. The results shows that the model can be used for FOREX prediction.
Neural networks are known to be effective function approximators. Recently, deep neural networks have proven to be very effective in pattern recognition, classification tasks and human-level control to model highly nonlinear realworld systems. This paper investigates the effectiveness of deep neural networks in the modeling of dynamical systems with complex behavior. Three deep neural network structures are trained on sequential data, and we investigate the effectiveness of these networks in modeling associated characteristics of the underlying dynamical systems. We carry out similar evaluations on select publicly available system identification datasets. We demonstrate that deep neural networks are effective model estimators from input-output data
This study presents a novel application and comparison of higher order neural networks (HONNs) to forecast benchmark chaotic time series. Two models of HONNs were implemented, namely functional link neural network (FLNN) and pi-sigma neural network (PSNN). These models were tested on two benchmark time series; the monthly smoothed sunspot numbers and the Mackey-Glass time-delay differential equation time series. The forecasting performance of the HONNs is compared against the performance of different models previously used in the literature such as fuzzy and neural networks models. Simulation results showed that FLNN and PSNN offer good performance compared to many previously used hybrid models.
Effectiveness of firefly algorithm based neural network in time series forecasting
The Foreign Exchange Market is the biggest and one of the most liquid markets in the world. This market has always been one of the most challenging markets as far as short term prediction is concerned. Due to the chaotic, noisy, and non-stationary nature of the data, the majority of the research has been focused on daily, weekly, or even monthly prediction. The literature review revealed that there is a gap for intra-day market prediction. Identifying this gap, this paper introduces a prediction and decision making model based on Artificial Neural Networks (ANN) and Genetic Algorithms. The dataset utilized for this research comprises of 70 weeks of past currency rates of the 3 most traded currency pairs: GBP\USD, EUR\GBP, and EUR\USD. The initial statistical tests confirmed with a significance of more than 95% that the daily FOREX currency rates time series are not randomly distributed. Another important result is that the proposed model achieved 72.5% prediction accuracy. Furthermore, implementing the optimal trading strategy, this model produced 23.3% Annualized Net Return.
In this paper we investigate and design the neural networks model for FOREX prediction based on the historical data movement of USD/EUR exchange rates. Unlike many other techniques of technical analysis which are based on price trends analysis, neural networks offer autocorrelation analysis and the estimation of possible errors in forecasting. This theory is consistent with the semi-strong form of the efficient markets hypothesis. The empirical data used in the model of neural networks are related to the exchange rate USD/EUR in the period 23.04.2012–04.05.2012. The results shows that the model can be used for FOREX prediction.
Neural networks are known to be effective function approximators. Recently, deep neural networks have proven to be very effective in pattern recognition, classification tasks and human-level control to model highly nonlinear realworld systems. This paper investigates the effectiveness of deep neural networks in the modeling of dynamical systems with complex behavior. Three deep neural network structures are trained on sequential data, and we investigate the effectiveness of these networks in modeling associated characteristics of the underlying dynamical systems. We carry out similar evaluations on select publicly available system identification datasets. We demonstrate that deep neural networks are effective model estimators from input-output data
This study presents a novel application and comparison of higher order neural networks (HONNs) to forecast benchmark chaotic time series. Two models of HONNs were implemented, namely functional link neural network (FLNN) and pi-sigma neural network (PSNN). These models were tested on two benchmark time series; the monthly smoothed sunspot numbers and the Mackey-Glass time-delay differential equation time series. The forecasting performance of the HONNs is compared against the performance of different models previously used in the literature such as fuzzy and neural networks models. Simulation results showed that FLNN and PSNN offer good performance compared to many previously used hybrid models.