FOURIER SERIES APPLICATION FOR MODELING “CHOCOLATE” KEYWORD SEARCH TRENDS IN GOOGLE TRENDS DATA

In some cases of regression modeling, it is very common to find a repeating pattern. To model this, course, the approach used must be in accordance with characteristics data. The Fourier series one proposed approaches, because has advantages modeling relationship patterns that tend repeat, such as cosine sine waves. subset nonparametric regression, which good flexibility modeling. this study, was applied search trend data for keyword "Chocolate" sourced from Google Trends. Generalized Cross-Validation (GCV) evaluation criteria. Based on results analysis, best obtained number oscillations five, indicated by minimum GCV value.