This document summarizes an approach for generating synthetic eye-tracking data using recurrent neural networks. The approach treats eye-tracking records as textual sequences and applies natural language processing and deep learning techniques. Specifically, a long short-term memory network is used to model eye movements as sequences. The model is trained on a dataset of over 2 million eye-tracking records from 59 participants. Experimental results show the model can accurately predict future eye movements, achieving around 75% accuracy. The generative model provides a way to synthetically create additional eye-tracking data when real datasets are limited or unavailable.