A tantalizing goal for systems neuroscience is to determine how the hippocampus and related brain areas support spatial navigation and memory. Continued progress towards this goal requires recording large populations of neurons simultaneously. Thanks to methodological advances it is now possible to record such populations, but it remains unclear how to efficiently analyze these large data sets. In this work we combine simulations, standard analyses, and machine learning to create an efficient pipeline for the analysis of spatial cells. Due to increased emphasis on determining how different cell types interact, we sought to develop a pipeline that accurately determines a cell’s functional cell type. To validate our pipeline, we first simulate populations of cells using parametric models of receptive field properties as well as linear - nonlinear poisson models. We then analyze each cell using our analysis suite which consisted of the commonly used analyses in the field. We determine a score from each analysis for each cell and use this vector of scores as input into our classification network. The network returns a probability for each cell type that can be compared with the true cell type for simulated cells. We demonstrate that the network achieves high accuracy regardless of cell type or simulation method. We then evaluate and comment on the contribution of each analysis to network accuracy. The code is publicly available via a public GitHub repository and has been designed such that new analyses can be added to the suite and the network easily retrained.