There is an increasing demand for indoor navigation and localization systems along with the increasing popularity of location based services in recent years. According to past researches, Bluetooth is a promising technology for indoor wireless positioning due to its cost-effectiveness and easy-to-deploy feature. This paper studied three typical fingerprinting-based positioning algorithms - kNN, Neural Networks and SVM. According to our analysis and experimental results, the kNN regression method is proven to be a good candidate for localization in real-life application. Comprehensive performance comparisons including accuracy, precision and training time are presented.