Current research on the impact of innovation networks focuses on the web and inter-organizational layers, with less consideration of individual behavior at the firm level. Interaction is an active action strategy that firms take when dealing with the external environment. Therefore, this study explores the mechanism of enterprise interaction on innovation development from the perspective of an innovation network. And measures enterprise interaction in three dimensions: affective interaction, resource interaction, and management interaction. The empirical results indicate that the three dimensions of enterprise interaction contribute significantly to technological innovation performance, and the realization of this role requires technological innovation capabilities (technological research and development capabilities, technological commercialization capabilities) to play a partially mediating role. The moderating effect of absorptive capacity between resource interaction, management interaction, and technological innovation capability is significant; however, the moderating effect between affective interaction and technological innovation capability is statistically insignificant. This study promotes the development of interaction theory to a certain extent, which helps enterprises build appropriate industrial chains in innovation networks and achieve rapid development.

Accurate product price forecasting is helpful for scientific decision-making and precise industrial planning. As a characteristic fruit that drives regional development, mango price prediction is of great significance to several economies. However, owing to the strong volatility of mango prices, forecasting is vulnerable to uncertainties and is very challenging. In this study, a deep-learning combination forecasting model based on a back-propagation (BP) long short-term memory (LSTM) neural network is proposed. Using daily mango price data from a large fruit wholesale trading center in China from January 2nd, 2014, to April 18th, 2022, mango price changes are learned and predicted to support the fruit industry. The results show that the root mean-square error, mean absolute percentage error, and the R2 determination coefficient of the BP-LSTM combination model are 0.0175, 0.14%, and 0.9998, respectively. The prediction results of the combined model are better than those of the separate BP and LSTM models. Furthermore, it best fits the actual price profile and has better generalizability.