Forecasting the Area Flowing of Graduate Employment Based on KRNN method

Abstract

It is hard to search the influence variables and to forecast the flowing of graduate employment due to the time series and complex factor inputs. Recently the neural network method has been successfully employed to solve the problem. However the forecasting result is not ideal due to the nonlinearity and noise. In this work, by combining Recurrent Neural Network (RNN) with Kernel Principal Component Analysis (KPCA), a KRNN model is presented, based on which, the area flowing of graduate employment is tried to be forecasted, and both the complex factor problem and time series problem has been dealt with. In the model, RNN with Kernel Principal Component Analysis (KPCA) and Principal Component Analysis (PCA) as the feature extraction is introduced in as comparison. And then by an empirical study with actual data from some high school of China, it is shown that the proposed methods can both achieve good forecasting performance comparing with NN method. And the KPCA method performs better than the PCA method.

Postgraduate entrant and employment forecasting using modified BP neural network with PSO

“…Where N the number of input variable dimension, M is the number of neural cell in hidden tier, L is the output variable dimension. W is the input weight matrix, V is the hidden tier weight matrixr, 1 B is hidden tier threshold vector, 2 B is the output tier threshold vector. Where the input vector is …”

“…Since china's opening up to the outside world, the control of postgraduate allocation has been shifted from administration to the market [1]. As important human resources of the developing of the overall strength of china and especially since the year 1997, which start to largescale enlarge postgraduate entrant, postgraduate entrant and employment has been remarkably change, thus it is very important problem that study and forecast postgraduate entrant and employment [2].…”

“…Those can't easily be transferred to a real mathematics model. Because of the nonlinear features and complicities, the conventional forecasting ways such as linear regression, expert experience system, ARMA and gray system theory could be disappointing in the accuracy and the velocity of the convergence [1]. In recent few decades, the development of artificial neural networks has bought forward a useful method to solve forecasting problem.…”