Zinabu Bekele Tadese ^1* Teshome Demis Nimani ² Kusse Urmale Mare ³ Fetlework Gubena ⁴ Ismail Garba Wali ⁵ Jamilu Sani ⁵

• ¹ Department of Health Informatics, College of Medical and Health Science, Samara University, Semera, Ethiopia
• ² Haramaya University, Harar, Dire Dawa, Ethiopia
• ³ Department of Nursing, College of Medicine and Health Sciences, Samara University, Semera, Ethiopia
• ⁴ Institute of Public Health, University of Gondar, Gondar, Amhara Region, Ethiopia
• ⁵ Federal University, Birnin Kebbi, Kalgo, Kebbi, Nigeria

Background: Fertility preferences indicate the number of children an individual would like to have, regardless of any obstacles that may stand in the way of fulfilling their aspirations. Despite the creation and application of numerous interventions, the overall fertility rate in West African nations particularly Nigeria is still high at 5.3 percent according to 2018 Nigeria demographic and health survey data. Hence this study aimed to predict the fertility preference among reproductive women in Nigeria by state-of-the-art machine learning techniques.Methods: Secondary data analysis from the recent 2018 Nigeria Demographic and Health survey dataset was employed using feature selection to identify predictors for building machine learning models. Data was thoroughly assessed for missingness and weighted to draw valid inferences. Six machine algorithms such as Logistic Regression, Support vector machine, K Nearest Neighbors, Decision Tree, Random Forest, XGBoost were employed on a total sample size of 37,581 in Python 3.9 version. Model performance was assessed using accuracy, precision, recall, F1 score, and AUC-ROC. Permutation and Gini techniques were used to identify the feature's importance.Results: Random Forest achieved the highest performance with accuracy (92%), precision (94%), recall (91%), F1-score (92%) and area under ROC (92%). Factors influencing fertility preferences were number of children, age group, and ideal family size. Region, contraceptive intention, ethnicity, and spousal occupation had moderate influence. Women's occupation, education, and marital status had a lower impact.This study highlights Machine Learning potential to analyze complex demographic data, revealing hidden influences on fertility preferences among Nigerian women. In conclusion, these findings can inform more effective family planning interventions, promoting sustainable development across Nigeria.