Predicting Customer Goals in Financial Institution Services: A Data-Driven LSTM Approach
By Andrew Estornell, Stylianos Loukas Vasileiou, William Yeoh, Daniel Borrajo, Rui Silva
Rating
1270
Battle Count: 153
Relevance
6/10
While not directly applicable to trading, the methods could be adapted for predicting investor behavior and goals
Implementation Complexity
7/10
Requires implementation of both LSTM and GNN architectures, as well as creation of state-space graph embeddings
Reproducibility
3/5
The paper provides details on the dataset and model architecture, but lacks specific hyperparameters and implementation details
About this paper
Methodology: LSTM with Graph Neural Network Embedding. Problem types: Classification, Time Series Forecasting.
The interactive Everscope explorer (charts, battles, favorites) loads below.