Machine learning feature space reduction techniques allow for vast feature spaces to be reduced with little loss or even significant improvements in the reliability of predictions of models. Microwave spectroscopy with feature spaces of over 8000 are not uncommon when considering magnitude and phase. Applying Machine learning techniques to this type of feature space allows for a quicker reduction and helps to identify the most suitable predictive features. The control of insect vectors that transmit diseases including malaria, visceral leishmaniasis and zika rely on the use of insecticide. These diseases affect millions, malaria alone accounted for 214 million new cases resulting in 438,000 deaths in 2015. One method used in controlling the vectors is through indoor residual spraying, applying insecticide to the wall surface inside houses. Alphacypermethrin is one of the insecticides that is currently sprayed in several countries for vector control. Quality assurance and monitoring of the control activities is challenging relying on the use of laboratory-reared insects. This was improved with a chemical based Insecticide Quantification Kit, but these assays have been challenging to operationalise. An electromagnetic sensor is being developed to investigate the potential to detect alpha-cypermethrin. Preliminary experiments were carried out to differentiate tiles sprayed with Technical Grade alpha-cypermethrin, wettable powder containing 5% alpha-cypermethrin and wettable powder with over dose of alpha-cypermethrin using a horn antenna at a frequency range between 1 GHz to 6 GHz. The experimental results indicated the potential use of electromagnetic waves to determine alpha-cypermethrin in a non-destructive manner.