Imbalanced Multimodal Attention-Based System for Multiclass House Price Prediction

House price prediction is an important problem for individuals, companies, organizations, and governments. With a vast amount of diversified and multimodal data available about houses, the predictive models built should seek to make the best use of these data. This leads to the complex problem of how to effectively use multimodal data for house price prediction. Moreover, this is also a context suffering from class imbalance, an issue that cannot be disregarded. In this paper, we propose a new algorithm for addressing these problems: the imbalanced multimodal attention-based system (IMAS). The IMAS makes use of an oversampling strategy that operates on multimodal data, namely using text, numeric, categorical, and boolean data types. A self-attention mechanism is embedded to leverage the usage of neighboring information that can benefit the model’s performance. Moreover, the self-attention mechanism allows for the determination of the features that are the most relevant and adapts the weights used according to that information when performing inference. Our experimental results show the clear advantage of the IMAS, which outperforms all the competitors tested. The analysis of the weights obtained through the self-attention mechanism provides insights into the features’ relevance and also supports the importance of using this mechanism in the predictive model.