In order to predict consumer behaviors, this paper proposes a consumption type prediction model using LSTM (Long Short Term Memory), a modification algorithm of RNN (Recurrent Neural Network). To do this, we derive and define age and gender consumption type patterns through Association Rule Analysis based on PrefixSpan algorithm using actual card consumption statistical data. Based on this, we used a pattern of daily consumption pattern as an input value, and constructed a model that predicts age and gender consumption patterns by learning the differences between the actual and forecast error rates in a week.
CITATION STYLE
Kim, J., & Moon, N. (2020). LSTM-Based Consumption Type Prediction Model. In Lecture Notes in Electrical Engineering (Vol. 536 LNEE, pp. 564–567). Springer. https://doi.org/10.1007/978-981-13-9341-9_97
Mendeley helps you to discover research relevant for your work.