Predicting Arpredicting Art Sales Trends Using Ai Modelst Sales Trends Using Ai Models

Artificial intelligence combined with cultural economics has provided new possibilities to predict the behavior of the market in the realm of the global art economy. The trend in art sales demands the combination of various modalities economic signals, aesthetic parameters, and social mood that can shape the sense of value. This paper presents a predictive model built using AI and based on structured data, the use of critic narratives, and images of art paintings based on hybrid learning architectures, comprising machine learning models (XGBoost, Random Forest) and deep learning models (CNN-LSTM and Transformer networks). The ensemble fusion model has good forecasting precision with an R2 of 0.94 and a large decrease in the mean error as compared to the standard econometric and single model baselines. Explainable AI methods, i.e., SHAP and Grad-CAM, are interpretations of transparency, which discloses the relative impact of visual, textual, and economic variables on the results of prediction. The framework was used to explain the benefits of data-driven intelligence to identify both measurable and non-quantifiable determinants of value in the art market using a multimodal dataset of 80,000 artworks that took place between 2010 and 2024. The results demonstrate the increasing importance of AI as a tool between computational analytics and cultural interpretation that allow making informed decisions by collectors, investors, and cultural policymakers

Analytics · Applications of artificial intelligence · Cultural intelligence · Econometric model · Ensemble learning · Modalities · Predictive analytics · Realm · Aesthetic Perception and Analysis · Art History and Market Analysis · Cultural Industries and Urban Development

• Understanding which cues people use to identify influencer marketing on Instagram

  Open Access•Sophie C Boerman, Céline M Müller•International Journal of…•2022

  Add to list