As there has been a rise in the usage of in silico approaches, for assessing the risks of harmful chemicals upon animals, more researchers focus on the utilization of Quantitative Structure Activity Relationship models. A number of machine learning algorithms link molecular descriptors that can infer chemical structural properties associated with their corresponding biological activity. Efficient and comprehensive computational methods which can process huge set of heterogeneous chemical datasets are in demand. In this context, this study establishes the usage of various machine learning algorithms in predicting the acute aquatic toxicity of diverse chemicals on Fathead Minnow (Pimephales promelas). Sample drive approach is employed on the train set for binning the data so that they can be located in a domain space having more similar chemicals, instead of using the dataset that covers a wide range of chemicals at the entirety. Here, bin wise best learning model and subset of features that are minimally required for the classification are found for further ease. Several regression methods are employed to find the estimation of toxicity LC50 value by adopting several statistical measures and hence bin wise strategies are determined. Through experimentation, it is evident that the proposed model surpasses the other existing models by providing an R2 of 0.8473 with RMSE 0.3035 which is comparable. Hence, the proposed model is competent for estimating the toxicity in new and unseen chemical.