Objective The association between chemical pollutant exposure， such as pesticides and chemical pollutants， and hypertension in adult residents of Shijiazhuang and Hangzhou was assessed using various machine learning methods.Methods A cross-sectional study was conducted in Shijiazhuang and Hangzhou， China from 2018 to 2019. A total of 496 participants were selected based on their individual characteristics， including， body measurements and routine blood tests， as well as pesticide and chemical pollutant exposure. Lasso was used to select features， which were fitted with logistic regression models and other machine learning methods to study the factors influencing hypertension. The effects of the different models were compared based on the area under the curve （AUC）.Results The Lasso feature selection results showed that pesticides and chemical pollutants， specifically， 4-CPA， PFOA， PFHxS and PFOS were significantly associated with hypertension. Among the machine learning models tested， the support vector machine model had the best performance （AUC=0.71）， which was better than the traditional logistic regression model （AUC=0.57）.Conclusion Exposure to the pesticide chemicals， 4-CPA， PFOA， PFHxS and PFOS， are important risk factors for hypertension. Additionally， machine learning models can be used to study epidemiological influencing factors and have an advantage in fitting non-linear relationships.