The Statistical Package for Social Sciences (SPSS) Statistics software suit was used to test the model's goodness of fit and its normal distribution. Combined with the actual pavement survey data these tools were used to verify the model. The research results show that: permafrost and water-rich conditions have the same effect on pavement roughness and bumping; four key factors, including pavement riding quality index (RQI), pavement bumping index (PBI), frozen soil and water-rich environmental factors have significant impact on pavement roughness and bumping. The prediction model adjusted R2 is 0.970, which is close to 1. The proposed model provides a high degree of fit and satisfies the assumption of normal distribution. When the PBI is from 87.5 to 95, the permafrost environmental factor is from 0.0002 to 0.0014, and the water-rich environmental factor is from 10.73 to 14.87, the prediction level of the model is the best. The model's RQI prediction value and the measured value has a degree of fit 0.987, which shows a good prediction effect. The prediction model can reasonably predict the roughness and the bumping of cement concrete pavement, which is of great significance to improve road traffic safety and to prolong the service life of cement concrete pavement in seasonal frost regions and water-rich areas.