It is not uncommon for low-quality olive oil to impersonate or adulterate extra virgin olive oil. To rapidly identify extra virgin olive oil adulteration, this paper proposes a portable Raman spectroscopy combined with an artificial neural network algorithm to identify extra virgin olive oil adulteration. First, mix low-quality and extra virgin olive oil according to different volume ratios and keep them still for 24 hours. Then, a portable Raman spectrometer is used to detect the Raman spectra of mixed oil samples with varying concentrations of adulteration. A quantitative analysis model is built based on the backpropagation neural network algorithm. Finally, the B3LYP/6-31+G (d, p) basis set of density functional theory is used to calculate the Raman spectrum of the main molecules of extra virgin olive oil, and the basis for quantitative analysis of adulteration of extra virgin olive oil is discussed from the mechanism. The experimental results show that the quantitative analysis of adulterated extra virgin olive oil with low-quality olive oil can be achieved using the back propagation neural network and Raman spectroscopy technology. The determination coefficient of the quantitative analysis model is 0.996, and the root mean square error is better than 0.017. Therefore, the back propagation neural network combined with Raman spectroscopy can effectively analyze the adulteration of extra virgin olive oil, providing a reliable technical reference for ensuring the stability of the domestic olive oil market and protecting the legitimate rights of consumers.