Though seemingly insubstantial in size, flying insects such as mosquitoes and fruit flies significantly impact humans. Specific species of fruit flies are responsible for widespread crop damage and spoilage whereas certain female mosquitoes harbor pathogens in their salivary glands, transmitting them to humans when biting (or blood feeding). Humans have historically addressed the issue with high volume insecticide spraying throughout at risk regions. But overuse has promoted resistance. There are now increasingly fewer insecticides that are effective with reduced risk to human health and/or ecological impact. Alternatively, by understanding the neural basis of insect behavior, it may be possible to identify novel strategies that address the need for both safety and long-term efficacy. In this paper, we studied the sensory responses of mosquitoes and the fruit fly Drosophila melanogaster to better understand the chemicals and neural pathway that drive simple behaviors (attraction and aversion). We were interested in building machine learning models to read the neural activity from live flies and predict behavior (attract vs. repel) in a set of different flies. Interestingly, although fruit flies (and insects in general) have many sensory receptors to reconstruct the chemical environment, we found that one pathway for detecting CO2, seen in many insects, was highly correlated with behavior, later confirming the activity recorded from this pathway, specifically a neuron named ab1C, was also predictive, according to many different machine learning algorithms.