The forecast on the customers of the member point platform built on the blockchain technology by ARIMA and LSTM

Based on the current blockchain technology, a new member point platform was built jointly by the companies from different industries this year. In order to make this platform more efficiently, we should make arrangement for logistics, current funds and supply-chain management system in advance. Therefore, the forecast on the customers of the platform is important for a system. In this paper, we showed the time series dataset abstracted from the member point platform system, gave a comparison of the long short-term memory (LSTM) neural network model and the autoregressive integrated moving average (ARIMA) model with the prediction effectiveness on the number of new increased users on this platform, and analyzed both disadvantages and advantages of the two models.