Commodities trend link prediction on heterogeneous information networks

Events can be defined as an action or a series of actions that have a determined theme, time, and place. Event analysis tasks for knowledge extraction from news and social media have been explored in recent years. However, there are still few studies that aim to enrich predictive models using event data. In particular, agribusiness events have multiple components to be considered for a successful prediction model. For example, price trend predictions for commodities can be performed through time series analysis of prices, but we can also consider events that represent knowledge about external factors during the training step of predictive models. In this paper, we present a method for integrating events into trend prediction tasks. First, we propose to model events and time-series information through heterogeneous information networks (HIN) that allow multiple components to be directly modeled through multi-type nodes and edges. Second, we learn features from HIN through network embedding methods, i.e., network nodes are mapped to a dense vector of features. In particular, we propose a network embedding method that propagates the semantic of the pre-trained neural language models to a heterogeneous information network and evaluates its performance in a trend link prediction. We show that the use of our proposed model language-based embedding propagation is competitive with state-of-art network embeddings algorithms. Moreover, our proposal performs network embedding incrementally, thereby allowing new events to be inserted in the same semantic space without rebuilding the entire network embedding.