Probabilistic model building in genetic programming: a critical review

2013 ◽  
Vol 15 (2) ◽  
pp. 115-167 ◽  
Author(s):  
Kangil Kim ◽  
Yin Shan ◽  
Xuan Hoai Nguyen ◽  
R. I. McKay
Keyword(s):  
Genetic Programming ◽  
Probabilistic Model ◽  
Critical Review ◽  
Model Building

scholarly journals A Study On Financial Time Series Forecasting And Symbolic Regression By Means Of A Hybrid Probabilistic Model-Building Cartesian Genetic Programming Methodology

2021 ◽  
Author(s):  
Mahsa Mostowfi
Keyword(s):  
Time Series ◽  
Stock Market ◽  
Genetic Programming ◽  
Probabilistic Model ◽  
Stock Price ◽  
Model Building ◽  
Symbolic Regression ◽  
Time Series Forecasting ◽  
Fusion Model ◽  
Regression Problems

This work proposes a hybrid algorithm called Probabilistic Incremental Cartesian Genetic Pro- gramming (PI-CGP), which integrates an Estimation of Distribution Algorithm (EDA) with Carte- sian Genetic Programming (CGP). PI-CGP uses a fixed-length problem representation and the algorithm constructs a probabilistic model of promising solutions. PI-CGP was evaluated on sym- bolic regression problems and next trading day stock price forecasting. On the symbolic regression problems PI-CGP did not outperform other approaches. The reason could be premature convergence and being trapped at a local minimum. However, PI-CGP was competitive at stock market forecasting. It was comparable to a fusion model employing a Hidden Markov Model (HMM). HMMs are extensively used for time-series forecasting. This result is promising considering the volatile nature of the stock market and that PI-CGP was not customized toward forecasting.

scholarly journals A Study On Financial Time Series Forecasting And Symbolic Regression By Means Of A Hybrid Probabilistic Model-Building Cartesian Genetic Programming Methodology

2021 ◽  
Author(s):  
Mahsa Mostowfi
Keyword(s):  
Time Series ◽  
Stock Market ◽  
Genetic Programming ◽  
Probabilistic Model ◽  
Stock Price ◽  
Model Building ◽  
Symbolic Regression ◽  
Time Series Forecasting ◽  
Fusion Model ◽  
Regression Problems

This work proposes a hybrid algorithm called Probabilistic Incremental Cartesian Genetic Pro- gramming (PI-CGP), which integrates an Estimation of Distribution Algorithm (EDA) with Carte- sian Genetic Programming (CGP). PI-CGP uses a fixed-length problem representation and the algorithm constructs a probabilistic model of promising solutions. PI-CGP was evaluated on sym- bolic regression problems and next trading day stock price forecasting. On the symbolic regression problems PI-CGP did not outperform other approaches. The reason could be premature convergence and being trapped at a local minimum. However, PI-CGP was competitive at stock market forecasting. It was comparable to a fusion model employing a Hidden Markov Model (HMM). HMMs are extensively used for time-series forecasting. This result is promising considering the volatile nature of the stock market and that PI-CGP was not customized toward forecasting.

Improved sampling using loopy belief propagation for probabilistic model building genetic programming

2015 ◽  
Vol 23 ◽  
pp. 1-10 ◽  
Author(s):  
Hiroyuki Sato ◽  
Yoshihiko Hasegawa ◽  
Danushka Bollegala ◽  
Hitoshi Iba
Keyword(s):  
Genetic Programming ◽  
Probabilistic Model ◽  
Model Building ◽  
Belief Propagation ◽  
Loopy Belief Propagation
Sign in / Sign up

Export Citation Format

Share Document