A mass of data is the foundation of adaptive forecasting model. However, the role of new incoming data will be gradually reduced and the performance of the model will become poor with the data increasing. In order to overcome the influence of “data saturation” on the weather forecast, the method of adaptive linear least square modeling algorithm considering forgetting factors is developed and applied in max min temperature forecast. The results show that this adaptive linear least square modeling algorithm considering forgetting factors is superior to the traditional adaptive linear modeling algorithm, it can reduce the effect of “data saturation” by using the forgetting factor, and it is possible to improve the model’s forecast accuracy by choosing the appropriate forgetting factors.