Forecasting Model for Vegetable Price Using Back Propagation Neural Network

The Agricultural sector needs more support for its development in developing countries like India. Price prediction helps the farmers and also the Government to make effective decision. Based on the complexity of vegetable price prediction, making use of the classification technique like neural networks such as self build up the model of Back-propagation neural network (BPNN) to predict vegetable price. A prediction model was set up by applying the neural network. Taking tomato as an example, the parameters of the model are analyzed through experiment. At the end of the result of Back shows accuracy percentage of the price prediction. Keywordsdata mining, neural networks Data mining is the process of extracting important and useful information from large sets of data Pardalos PM, Resende M [1]. Data mining in agriculture is a novel research vegetables and crops but also harvesting large amount of data. Data mining provides the methodology to transform these data into useful information for decision making. Vegetable price changes fast and unstable which makes great impact in our daily life. Vegetable price has attributes such as high nonlinear and high noise. So, it is hard to predict the vegetable price. Data mining classification techniques can be used to develop an innovative model to predict the marke agriculture for forecasting the market price for the respective commodities and also useful for farmers to plan their crop cultivation activities so that they could fetch more price in t forecast price for planning and implementation of agriculture development programs to stabilize the market price for the respective commodity. Consumers can use this price prediction for their daily lifestyle pla innovative application is not only useful for farmers and consumers but also useful for agriculture planning; framing polices and schemes in agriculture and market planning. Time series forecasting takes an existing series of data to predict future value. Data mining classification technique such as Neural Network plays an important role in non-linear time series prediction [2, 3, 4]. There are many kinds of prediction method on basis of Neural Network, among them the application of BP Neural Ne There has been large number of studying on forecasting of vegetable price. This section presents a very brief review of the related and recent studies. Alionue Dieng [5] investigated the performance for forecasting vegetable prices and to make recommendation to potential user. The author used two forecasting approaches. The forecasting methods used consist of three alternative parameter models and a non parametric model. The parametric models consist of the naïve model, exponential smoothing models and box interacted moving average model (ARIMA). The non paramedic model uses the spectral analysis. The author collected monthly average price of tomato, potato and onion for t parametric model and non parametric model were used to generate forecasting of potato, tomato and onion price. Based on the results the parametric models would be recommended for forecasting vegetable price. Among t ARIMA model receives high priority. Koffi N.Amegbeto [6] presented a study of examined the dynamics of selected vegetable prices and the quantities supplied to the main fruit and vegetable market in Kabul, Afghanistan. Forecasting models were develope from Aug 2004 to Dec 2005. The results show that prices and supplies of certain vegetables were erratic and Vol. 2: No. 2, July September 2012 N.Hemageetha Asst. Professor Department of Computer Science Govt. Arts College for Women Salem, India [email protected] characteristics of data mining -adapt, self-study and high fault tolerance, to -propagation neural network , back-propagation (BP), vegetable price