Low temperature gathering production process technology is an effective method to reduce energy consumption and improve production efficiency in oilfield. However, the feasibility ambiguity of low-temperature gathering process technology has prevented the technology from being widely promoted in oilfield production. Combining oilfield field production data, in this paper, entropy weight method and grey incidence analysis method are used to correlate the influencing factors of low-temperature gathering technology, and the back propagation (BP) neural network algorithm establishs the low-temperature gathering feasibility prediction model.