Weightless Neural Network for High Frequency Trading

Alves, Samara; Caarls, Wouter; Lima, Priscila M. V.

doi:10.1109/ijcnn.2018.8489445

Cited by 8 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For intraday trading, flat fluctuations are the most likely cause of stop‐losses and so it is vital to reduce their number (Alves et al, 2018) as a pre‐processing priority before training. To indicate the minimum stop‐loss,

P_{2 +}

and

P_{2 -}

boundaries are created which are approximately equal to two standard deviations of the flat movement (fluctuation) distributions.…”

Section: A Novel Methods To Reduce Big Financial Datamentioning

confidence: 99%

Reduction of financial tick big data for intraday trading

Milke,

Luca,

Wilson

2024

Expert Systems

View full text Add to dashboard Cite

Various neural network architectures are often used to forecast movements in financial markets. Most research in quantitative analytics in finance uses interval financial data as this reduces the raw tick big data, but the averaging can lose key behaviour patterns. This work presents an alternative novel method to reduce raw tick data whilst retaining important information for training, as demonstrated with intraday trading using the EURO/USD currency pair. This time series reduction method focuses on short periods preceding significant movements in financial features and allows the most popular neural network architectures to be applied using less powerful but more readily available computer resources. It is shown that the proposed data preprocessing method for machine learning and other AI‐techniques successfully reduced the size of the selected dataset covering a three‐year period (2018–2021) by 275 times.

show abstract

P_{2 +}

and

P_{2 -}

boundaries are created which are approximately equal to two standard deviations of the flat movement (fluctuation) distributions.…”

Section: A Novel Methods To Reduce Big Financial Datamentioning

confidence: 99%

Reduction of financial tick big data for intraday trading

Milke,

Luca,

Wilson

2024

Expert Systems

View full text Add to dashboard Cite

show abstract

“…This section has analyzed the related study, innovations and executional scenarios of existing models and approaches. The author F. Kamalov [29]. Traditional Neural Networks have few limitations for simulating the data as it is dependable on hardware structure with parallel processing.…”

Section: Related Workmentioning

confidence: 99%

Auto-Regressive Integrated Moving Average Threshold Influence Techniques for Stock Data Analysis

Singh¹,

Henge²,

Mandal³

et al. 2023

IJACSA

View full text Add to dashboard Cite

This study focuses on predicting and estimating possible stock assets in a favorable real-time scenario for financial markets without the involvement of outside brokers about broadcast-based trading using various performance factors and data metrics. Sample data from the Y-finance sector was assembled using API-based data series and was quite accurate and precise. Prestigious machine learning algorithmic performances for both classification and regression complexities intensify this assumption. The fallibility of stock movement leads to the production of noise and vulnerability that relate to decision-making. In earlier research investigations, fewer performance metrics were used. In this study, Dickey-Fuller testing scenarios were combined with time series volatility forecasting and the Long Short-Term Memory algorithm, which was used in a futuristic recurrent neural network setting to predict future closing prices for large businesses on the stock market. In order to analyze the root mean squared error, mean squared error, mean absolute percentage error, mean deviation, and mean absolute error, this study combined LSTM methods with ARIMA. With fewer hardware resources, the experimental scenarios were framed, and test case simulations carried out. Keywords-Dickey-Fuller test case (DF-TC); recurrent neural network (RNN); root mean square error (RMSE); long short-term memory (LSTM); machine learning (ML); auto-regressive integrated moving average (ARIMA)I.

show abstract

“…These non-linear algorithms usually outperform than linear models because they can learn the non-linear relationships between different features. With the development of deep learning models for compute vision, natural language, and speech recognition, some researchers have attempted to learn hidden relationship from features using deep neural networks (DNN) [10], recurrent neural networks (RNN) [11], long short-term memory (LSTM) [12], convolutional neural network (CNN). While at the production level of high-frequency trading, the fatal shortcoming of deep learning models is the time cost of prediction, which is usually millisecond, whereas the cost time of the highfrequency trading strategy is only 10 microseconds.…”

Section: A High-frequency Tradingmentioning

confidence: 99%

Reinforcement Learning for Stock Prediction and High-Frequency Trading With T+1 Rules

Zhang

Yin

Zhao³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The high-frequency trading framework for the price trend prediction model and trading strategy has been a popular approach for T+0 trading in the stock market. The prediction model is used to predict price trends, and the trading strategy is used to determine the price and volume of the order. Most trading strategies consist of multiple trading logic associated with certain tuning parameters. These parameters significantly affect the profitability of high-frequency trading frameworks. There are two main disadvantages of this framework: 1) the price trend prediction model can not adapt to the current market data distribution, and 2) the trading strategy can not adapt to the current market conditions automatically. Thus, the framework cannot always maintain positive revenue. To address this problem, we propose a novel dynamic parameter optimization algorithm based on reinforcement learning for stock prediction and trading, and to generate an adaptive trading framework. First, we use a rolling model training method for stock price trend prediction. Second, we regard each set of strategy parameters as action and devise an inverse reinforcement learning algorithm for the reward function to accurately estimate the reward of each action. Because of the T+1 trading rules of the Chinese stock market, we consider the constraint of limited short position in the reward function. Finally, a reward-enhanced upper confidence bound (UCB) selection algorithm is proposed to automatically optimize the parameters of the trading logic in real-time trading. The experimental results show that our method achieves competitive performance in the Chinese stock market.

show abstract

Weightless Neural Network for High Frequency Trading

Cited by 8 publications

References 18 publications

Reduction of financial tick big data for intraday trading

Reduction of financial tick big data for intraday trading

Auto-Regressive Integrated Moving Average Threshold Influence Techniques for Stock Data Analysis

Reinforcement Learning for Stock Prediction and High-Frequency Trading With T+1 Rules

Contact Info

Product

Resources

About