To accommodate the rapidly increasing demand for connected infrastructure, automation for industrial sites and building smart cities, the development of Internet of Things (IoT)-based solutions is considered one of the major trends in modern day industrial revolution. In particular, providing high precision indoor positioning services for such applications is a key challenge. Wi-Fi fingerprint-based indoor positioning systems have been adapted as promising candidates for such applications. The performance of such indoor positioning systems degrade drastically due to several impairments like noisy datasets, high variation in Wi-Fi signals over time, fading of Wi-Fi signals due to multipath propagation caused by hurdles, people walking in the area under consideration and the addition/removal of Wi-Fi access points (APs). In this paper, we propose data pre- and post-processing algorithms with deep learning classifiers for Wi-Fi fingerprint-based indoor positioning, in order to provide immunity against limitations in the database and the indoor environment. In addition, we investigate the performance of the proposed system through simulation as well as extensive experiments. The results demonstrate that the pre-processing algorithm can efficiently fill in the missing Wi-Fi received signal strength fingerprints in the database, resulting in a success rate of 88.96% in simulation and 86.61% in a real-time experiment. The post-processing algorithm can improve the results from 9.05–10.94% for the conducted experiments, providing the highest success rate of 95.94% with a precision of 4 m for Wi-Fi fingerprint-based indoor positioning.