Back-propagation(bp) neuralnetwork has been widely used for dealing with large-scale nonlinear problems. However, the bpalgorithm is powerless, when in the face of singular sample data, which with high characteristi...
详细信息
Back-propagation(bp) neuralnetwork has been widely used for dealing with large-scale nonlinear problems. However, the bpalgorithm is powerless, when in the face of singular sample data, which with high characteristic dimensional and small sample size. Too many input makes the network structure is difficult to determine, cause slow convergence rate;fewer number of samples makes the network training is not complete, thereby affecting the recognition precision of the neuralnetwork. Aiming at these deficiencies, in this paper proposed the optimized bp neural network algorithm based on the partial least squares(PLS) algorithm(PLS-bpalgorithm), firstly the new algorithm reduce feature dimension for singular sample data used PLS method, which can fully take into account the level of correlation characteristic variables and the dependent variables, then get the low-dimensional data is used for network training and simulation. New algorithm simplifies the network structure and improves the network training speed and recognition precision.
The current inventory problem has become the key issue in the enterprise survival and *** this paper,we take "Taobao" as an example to conduct a detailed study of the inventory of the high conversion rate ba...
详细信息
The current inventory problem has become the key issue in the enterprise survival and *** this paper,we take "Taobao" as an example to conduct a detailed study of the inventory of the high conversion rate based on data ***,by using a funnel model to predict the conversion of the commodities on the critical path,we capture the factors influencing the consumer decision-making on each key point,and propose corresponding solutions of improving the conversion rate;Second,we use bp neural network algorithm to predict the goods traffic,and then obtain the corresponding weights by the relation analysis and the output of the goods traffic by the input of large data sample goods;Third,we can predict the inventory in accordance with the commodity conversion rate and flow prediction,and amend the predicted results to get accurate and real-time inventory forecast,avoiding the economic loss due to the inaccurate inventory.
暂无评论