Fast learning and predicting of stock returns with virtual generalized random access memory weightless neural networks

被引：4

作者：

De Souza, Alberto F. ^{[2
]}

Freitas, Fabio Daros ^{[1
]}

Coelho de Almeida, Andre Gustavo ^{[2
]}

机构：

[1] Receita Fed Brasil, Vitoria, ES, Brazil

[2] Univ Fed Espirito Santo, Dept Informat, Vitoria, ES, Brazil

来源：

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE | 2012年 / 24卷 / 08期

关键词：

high-performance time-series prediction; weightless neural networks; high-frequency trading;

D O I：

10.1002/cpe.1772

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

We employ virtual generalized random access memory weightless neural networks, VG-RAM WNN, for predicting future stock returns. We evaluated our VG-RAM WNN stock predictor architecture in predicting future weekly returns of the Brazilian stock market and obtained the same error levels and properties of baseline autoregressive neural network predictors; however, our VG-RAM WNN predictor runs 5000 times faster than autoregressive neural network predictors. This allowed us to employ VG-RAM WNN predictors to build a high frequency trading system able to achieve a monthly return of approximately 35% in the Brazilian stock market. Copyright (C) 2011 John Wiley & Sons, Ltd.

引用

页码：921 / 933

页数：13

共 20 条

[1] The efficacy of neural networks in predicting returns on stock and bond indices
Desai, VS
Bharati, R
[J]. DECISION SCIENCES, 1998, 29 (02) : 405 - 425
[2] A generalized reinforcement learning scheme for random neural networks
Ricardo Lent
[J]. Neural Computing and Applications, 2019, 31 : 2699 - 2716
[3] A generalized reinforcement learning scheme for random neural networks
Lent, Ricardo
[J]. NEURAL COMPUTING & APPLICATIONS, 2019, 31 (07): : 2699 - 2716
[4] Fast and Accurate Weight Updating Strategy for Resistive Random-Access Memory (RRAM)-Based Neural Networks
Feng, Yulin
Huang, Peng
Chen, Yiyang
Zhang, Yizhou
Li, Ruiyi
Zhou, Zheng
Liu, Lifeng
Liu, Xiaoyan
Kang, Jinfeng
[J]. IEEE ELECTRON DEVICE LETTERS, 2023, 44 (03) : 416 - 419
[5] Use of Magnetoresistive Random-Access Memory as Approximate Memory for Training Neural Networks
Locatelli, Nicolas
Vincent, Adrien F.
Querlioz, Damien
[J]. 2018 25TH IEEE INTERNATIONAL CONFERENCE ON ELECTRONICS, CIRCUITS AND SYSTEMS (ICECS), 2018, : 553 - 556
[6] Predicting Stock Movements: Using Multiresolution Wavelet Reconstruction and Deep Learning in Neural Networks
Peng, Lifang
Chen, Kefu
Li, Ning
[J]. INFORMATION, 2021, 12 (10)
[7] A Class Incremental Learning and Memory Fusion Method Using Random Weight Neural Networks
Li, De-Peng
Zeng, Zhi-Gang
[J]. Zidonghua Xuebao/Acta Automatica Sinica, 2023, 49 (12): : 2467 - 2480
[8] Predicting stock market returns from malicious attacks: A comparative analysis of vector autoregression and time-delayed neural networks
Khansa, Lara
Liginlal, Divakaran
[J]. DECISION SUPPORT SYSTEMS, 2011, 51 (04) : 745 - 759
[9] Contrasting Advantages of Learning With Random Weights and Backpropagation in Non-Volatile Memory Neural Networks
Bennett, Christopher H.
Parmar, Vivek
Calvet, Laurie E.
Klein, Jacques-Olivier
Suri, Manan
Marinella, Matthew J.
Querlioz, And Damien
[J]. IEEE ACCESS, 2019, 7 : 73938 - 73953
[10] Fast Power Control Adaptation via Meta-Learning for Random Edge Graph Neural Networks
Nikoloska, Ivana
Simeone, Osvaldo
[J]. SPAWC 2021: 2021 IEEE 22ND INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (IEEE SPAWC 2021), 2020, : 146 - 150

← 1 2 →