This research evaluates an automatic cash payment system using an ESP32 microcontroller integrated with a bill acceptor, a Rp1000 coin acceptor, and a coin hopper. The system is designed to accept banknote and coin payments and dispense change automatically. The system was fully tested for 40 transactions. Results showed a success rate of 87.5% with the most problems being the incorrect reading of banknotes and coin positioning. The system shows high potential for use in vending machines or self-service platforms Keywords: Indoor Positioning System, Wi-Fi RSSI-Fingerprint, Multivariate Gaussian Mixture Model, Android Application, Accuracy.
                        
                        
                        
                        
                            
                                Copyrights © 2025