Study of forecasting on time series data by nearest neighbor method

Methods of forecasting on time series data by auto-regressive model, neural networks model and chaotic theorem are proposed. The methods are said to b e complicated for forecasting calculations. In this paper, a simple forecas ting algorithm by the nearest neighbor method is discussed. It is applied t o forecasting on a monthly average temperature in Sendai city to confirm pe rformance. The actual results indicate that the nearest neighbor method has similar performance to the auto-regressive model in forecasting on time-se ries data.