Localization is a hot topic in networking industry and falls into two categories: indoor localization and outdoor localization. Indoor localization takes place inside a building or other structure, whereas outdoor localization takes place outside a wall or building. The most common example of outdoor localization is GPS, but it is ineffective for indoor localization due to obstructions like walls in a house. Although there are many studies on indoor localization, they still lack to consider the presence of human body and other obstructing factors causing drop of localization accuracy. Therefore, this paper focuses on investigating indoor localization along with the presence of human body and a number of transmitters. This study concentrates on creating the best accurate model to predict the location of smartphones in the indoor environment. The dataset has been collected from the receiving signal strength using three different brands of smartphones, namely, Itel, Tecno, and Infinix, since there is a slight difference in terms of signal receiving capacity. Then, we ran successive experiments with DT, KNN, and SVM in comparison with a recurrent algorithm (BiLSTM). From the experiments, we observed that BiLSTM outperformed DT, KNN, and SVM with prediction accuracy of 78%. From our experimental results, we concluded that BiLSTM is best suited for indoor localization.