DATA-DRIVEN PROMOTION STRATEGIES FOR FOLK ARTISTS

Abstract

The folk artists are very important in the process of conserving the intangible cultural heritage, however, their presence and access to the market are restricted by the disjointed promotional channels, informal marketing and lack of data-driven decisions. As the digital platforms and social media, as well as online marketplaces, continue to grow, there is an expanding possibility to use data analytics to advance reach, sustainability, and economic resilience of the folk art communities. This research aims, first of all, to design and test the data-driven promotion strategies and maximize the audience, engagement, and sales outcomes of folk artists without interfering with the culture. The research is based on a mixed-method, data-driven approach, which is an integration of descriptive analytics, prediction models based on machine learning, and audience segmentation methods. Materials of digital interactions obtained in the social media platforms, online exhibitions and e-commerce portals are processed with the help of feature extraction, clustering and supervised learning models to determine the major visibility and demand drivers. Random Forest and Gradient Boosting models are used to predict the probability of engagement and conversion, and the effectiveness of promotional strategy is tested with the help of A/B testing. The results of these experiments show that data-intensive promotion strategies enhance the audience engagement rate by 28-35 percent and sales conversion rate by 22-27 percent in comparison with conventional and intuition-based promotion. The values of precision and recall (greater than 0.85) in engagement prediction suggest that the model performs well. The results indicate the importance of individual content timing, platform-specific approach, and demographic targeting. Altogether, the given framework offers a scalable, evidence-based framework of empowering folk artists, making an informed promotional decision, and facilitating the long-term sharing of cultural heritage in digital ecosystems.