Explore chapters and articles related to this topic
Random Forest and Grey Methodology in Dynamic Portfolio Selection
Published in Noura Metawa, M. Kabir Hassan, Saad Metawa, Artificial Intelligence and Big Data for Financial Risk Management, 2023
Tihana Škrinjarić, Silvija Vlah Jerić
In this chapter, RF is used for regression, i.e. for forecasting stock market index value based on its previous values (including also high and low values, as well as returns) and selected technical indices. The technical indices used are the same as were used in the research by Vlah Jerić (2021, 2020a,b). The description of calculations of those indicators is omitted here since they are done exactly as suggested by Bruni et al. (2016). The calculations include choosing certain parameters and those were set at values often used as defaults by traders and scientists in intraday trading. The indicators used are the following: Momentum over five periods (MOM),Exponential moving average (EMA) over 12 and 26 periods (EMA12 and EMA26, respectively),Moving average convergence/divergence with 12, 26, and 9 time periods (respectively) selected as three parameters needed for calculation (MACD),Return on investment (ROI) over 10, 20, and 30 periods (ROI10, ROI20, and ROI30, respectively),Relative strength index (RSI) over 10, 14, and 30 periods (RSI10, RSI14, and RSI30, respectively),Stochastic relative strength index (SRSI) over 10, 14, and 30 periods (SRSI10, SRSI14, and SRSI30, respectively),Average true range over 14 periods (ATR),Average directional index over the last 14 periods (ADX),Williams %R over 14 periods (WPR),Commodity channel index over 20 periods (CCI), andUltimate oscillator with 7, 14, and 28 time periods (respectively) selected as three parameters needed for calculation (UO).
A fuzzy neural network combined with technical indicators and its application to Baltic Dry Index forecasting
Published in Journal of Marine Engineering & Technology, 2019
Chien-Chang Chou, Keng-Shou Lin
CCI method was initially introduced by Donald (1980). It is calculated as the difference between the typical price of a commodity and its simple moving average, divided by the mean absolute deviation of the typical price. CCI usually is with a factor of 0.015. The CCI equation is listed as follows. Generally, CCI<−100 means the price has a downward trend. CCI >100 means the price has an upward trend. −100 < CCI <100 means the price has a non-stable trend. where pt is the typical
Blended computation of machine learning with the recurrent neural network for intra-day stock market movement prediction using a multi-level classifier
Published in International Journal of Computers and Applications, 2021
Krishna Kumar, Md. Tanwir Uddin Haider
Commodity Channel Index(CCI) is a technical indicator used to identify the market trend by visualizing the overbought and oversold conditions. where typical price (TP) is the mean of the IH, IL, and ICP; constant = 0.015; and SD = standard deviation of typical price, n = 14.