 This paper examines the relationship between electricity consumption and traffic volumes in Chicago. It uses long short-term memory, LSTM, networks to model electricity consumption patterns of ZIP codes based on the traffic volume of the same ZIP code and nearby ZIP codes. For analyses were conducted to identify inter-relationships, correlation between two-time series, temporal relationships, spatial relationships, and prediction of electricity consumption based on the total traffic volume. From over 250 models, it was found that there are complex inter-relationships between travel demand and electricity consumption. Additionally, it was observed that model performance varied across Chicago. This article was authored by Ali Muvahidi, Amir Bahadur Parsa, Anton Roskov, and others.