Wavelets in Combination with Stochastic and Machine Learning Models to Predict Agricultural Prices

Wavelet decomposition in signal processing has been widely used the literature. The popularity of machine learning (ML) algorithms is increasing day by agriculture, from irrigation scheduling and yield prediction to price prediction. It quite interesting study wavelet-based stochastic ML models appropriately choose most suitable wavelet filters predict agricultural commodity prices. In present study, some popular filters, such as Haar, Daubechies (D4), Coiflet (C6), best localized (BL14), least asymmetric (LA8), were considered. Daily wholesale data onions three major Indian markets, namely Bengaluru, Delhi, Lasalgaon, illustrate potential different filters. performance was compared with that benchmark models. observed that, general, combination outperformed other Moreover, Haar filter followed application random forest (RF) model gave better accuracy than combinations well individual