Document Type : Research Article
Author
Researcher
Abstract
In this article supply demand based on prices volumes are extracted as measure of swaps between two or more indexes by neural network for recommend Market Makers to increase performance of Large Traded Volumes in real time Markets Quotes. Neural network are widely applicable tools for develop operators performances in financial market applications. In classic economy when an equilibrium was Unbalanced must be a side of supply or demand was over than other one.in more indexes decisions for check balance condition between more than two indexes in real time market a neural network classification trigger is good suggestion. other methods such as indicators oscillators and numerical methods and statistical methods were been slow. The latency of candle data in clients solved by time stamp in log file and export of these triggers can draw by graphical Line or shape in data.an equilibrium point as middle of these balances for pairs of indexes are connected with triangle shape.
Keywords
,Cambridge University Press, 2008.
[2] Kamruzzaman, Joarder and Begg, Rezaul and Sarker, Ruhul, Arti cial neural networks in nance and manufacturing, IGI Global, 2006.
[3] Voit, Johannes and Lourie, Robert W, The statistical mechanics of nancial markets, Physics today, Springer, 2002.
[4] Petropoulos, A., Siakoulis, V., Panousis, K. P., Christophides, T., Chatzis, S, A Deep Learning Approach for Dynamic Balance Sheet Stress Testing, arXiv:2009.11075, arXiv preprint, 2020.
[5] Hwang, H. J., Jang, J. W., Jo, H., Lee, J. Y, Trend to equilibrium for the kinetic Fokker-Planck equation via the neural network approach, Journal of Computational Physics, 419, 109665, 2020.
[6] Hill, E., Bardoscia, M., Turrell, A, Solving heterogeneous general equilibrium economic models with deep reinforcement learning, arXiv:2103.16977, arXiv preprint, 2021.
[7] He, P, Essays on Demand Estimation, Financial Economics and Machine Learning, Columbia University, Columbia University, 2019.
[8] Neisy, A., Peymany, M, Modeling of Tehran Stock Exchange Overall Index by Heston Stochastic Differential Equation, Economics Research, 14(53), 143-166, 2014.
[9] Campoli, L., Kustova, E., Maltseva, P, Assessment of Machine Learning Methods for State-to-State Approach in Nonequilibrium Flow Simulations, Mathematics, 10(6), 928, 2022.
[10] Shahrokhabadi, M. A., Neisy, A., Perracchione, E., Polato, M, Learning with sub-sampled kernel-based methods, Environmental and nancial applications, Dolomites Research Notes on Approximation, 2019.
[11] Valaitis, V., Villa, A, A Machine Learning Projection Method for Macro-Finance Models, FRB of Chicago Working Paper, FRB of Chicago Working Paper, 2021.
)