Hong He

Five years after the implementation of the tourism precision poverty alleviation strategy, how effective it has been in alleviating poverty remains to be tested. This study, through a study of 241 farm households in 10 national tourism poverty alleviation key villages in the Qinba Mountain region of Hanzhong, southern Shaanxi, finds that rural tourism has contributed to a general increase in farm household income, but the effect of income increase varies significantly between households that have escaped poverty and non-poor households, and there is no significant difference in income between those who participate in tourism and those who do not. The study concludes that the poverty-reducing effects of tourism are conditional, with the poor quality of human capital being the main obstacle to farm households’ income growth, the institutional mechanism for tourism participation is inadequate, effective farm household tourism participation is significantly low, and non-farm work constitutes a substitute for farm households’ tourism livelihood options. The primary stage tourism scenic spots have a limited role in driving the income of farming households, and the geographical location limits the effective participation of farming households. Accordingly, the following countermeasures are proposed: (1) in terms of strategic decision-making options, establish a screening mechanism for tourism participation in poverty alleviation and implement diversified poverty governance; (2) in terms of tourism development strategies, encourage the integration of multiple industries and synergistic development, realize the two-way interaction of “+ tourism” and “tourism +”; (3) in terms of development methods, adhere to the participatory development path, improve the institutional mechanism for tourism participation, stimulate the endogenous motivation of farmers, and explore the dynamic participation path of “bottom-up”. (4) In the development of endogenous power, strengthen skills training, improve the comprehensive quality of farmers and their participation level and ability; (5) In the coordination and protection, play the coordinating and leading role of grass-roots party building, and continuously cultivate and strengthen tourism cooperative organizations.

To accurately predict the economic development of each industry in different types of regions, a deep convolutional neural network model was designed for predicting the annual GDP; GDP growth index; and primary, secondary and tertiary industry growth values of each. In the model, raw industrial data are preprocessed by a normalization operation and subsequently transformed by the BoxCox method to approach the normal distribution. Panel data of consecutive years are constructed and used as input to the deep convolutional neural network, and industrial data of year t + 1 are used as the output of the network. Simulation experiments were conducted to analyze 23 years of industrial economic data from 31 provinces, municipalities, and autonomous regions in China. The experimental results show that R-squared value is larger than 0.91 for all 31 provinces and root mean squared log errors (RMSLE) of all regions are less than 0.1, which demonstrate that the proposed method achieves high prediction accuracy with generalization capability and can accurately predict the economic growth trends of different types of regions.

To enhance the sustainability of the regional economy, this study attempts to integrate historical big data of multiregional and multi-industry economic indicators, aiming to explore and discover the correlations among regions, industries, or cross-regional economic indicators. In this paper, two correlation analysis models (the 2-order correlation model and the elastic-net regularized generalized linear model) are used to conduct a correlation analysis study of multiregional and multi-industry economies, and 20 years of historical data from 9 prefecture-level cities in Shaanxi (778 indicators in total) are analyzed empirically. The results show that the proposed method can mine complex correlations from economic big data.