A Hybrid Fuzzy-Markov Chain Model with Weights and its Application in Prediction Fertility Rate in Iraq

Abstract

This research introduces a new method, termed the Hybrid Fuzzy-Markov Chain Model with Weights (HF-MCW), and employs it to forecast fertility rates in Iraq. The HFMCW model combines fuzzy logic to address uncertainties in input data with Markov chain analysis to capture the sequential patterns inherent in fertility rate dynamics. Additionally, the model incorporates weights to account for the varying significance of factors affecting fertility rates. Through the utilization of historical fertility data and pertinent socio-economic indicators, the HFMCW model presents a robust framework for predicting fertility trends. Data for this study was collected from the website Macrotrends about fertility rate in Iraq for 73 years during from the period (1950–2023). The results show that the hybrid model enhances prediction precision compared to conventional methods by effectively managing data imprecision through fuzzy logic and capturing probabilistic state transitions with Markov chains and the use of weights allows the model to adjust to the varying significance of different influencing factors, providing flexibility to account for changes in socio-economic conditions, healthcare advancements, and policy effects on fertility rates.