Possible food and drug interactivities could alter the intended efficiency of particular therapeutics in medical practice. The increasing number of multiple-drug prescriptions is prone to the rise of drug-drug and drug-food/drug-nutrient interactions. The presence of these unfavorable interactions leads to other implications e.g., the decline in medicament’s effect, the withdrawals of various medications, and detrimental impacts on the patients’ health, etc. Yet the importance of drug-food/drug-nutrient interactions is remained underestimated, as the number of studies referring to these topics is constrained. Recently, state-of-the-art machine learning (ML) models have been created to unveil the hidden influences between drug and food compounds. However, there were still some limitations in terms of data mining, data input, and detailed annotations. In this study, we proposed a novel ML-based prediction model that could address most drawbacks of other models. A total of 4,384 food and 334 drug constituents were included in our training set, and two validation sets (containing 140,546 and 179 samples, respectively) were prepared for the model assessment. PyBioMed package has been used to obtain 3,780 chemical features, and then feature selection has been performed to select 25 most important features. The performance of our model was highly promising, as the accuracy score was 88.28% and 92.18% on the first and second validation set, respectively. More importantly, the DFIPred is capable of exhibiting the output recommendation about the interaction of any given pair of one drug and one food constituent based on their compound names. We believe that our model would contribute to the development of better and more powerful models used for the prediction of drug-food interactions in the future.