With environmental computing and agricultural engineering fast emerging as important factors determining agricultural productivity, Information and Communication Technology (ICT) is playing an extra role in improving advanced agricultural applications. This paper proposes a machine learning-based crop recommendation system based on environmental and soil parameters to enhance the decision-making process in crop selection. The study made use of ICT tools for collection and processing of data on nitrogen (N), phosphorus (P), potassium (K), temperature, humidity, pH, and rainfall as a way of encouraging data-based decisions for farmers. Four machine learning algorithms were put to the test, Logistic Regression, Support Vector Machine (SVM), Random Forest, and Gradient Boosting, where the Random Forest algorithm scored the highest accuracy (99.32%). The main predictors of crop recommendations were soil nutrients, temperature, humidity, rainfall, and pH levels. The study demonstrates how environmental computing and engineering can enhance agricultural productivity and ensure sustainability through ICT-based solutions.