Sistem Informasi Manajemen Keuangan Pribadi Dengan Input Suara Dan Berbasis Iot

Abstract

The increasing need for practical personal financial management, especially among students and young professionals, highlights the challenges of recording small daily expenses such as parking or food transactions. Manual recording often leads to inconsistencies due to forgetfulness or inconvenience. To address this issue, this study develops an Internet of Things (IoT) based personal financial management system integrating smartwatch and smartphone devices with voice input features. Voice commands are transcribed into text using Google Speech-to-Text, while transaction information such as type, description, and nominal value is extracted using the Boyer-Moore string matching algorithm. The system was implemented using Android technology with real-time synchronization through Firebase Firestore. Functional testing through blackbox methods showed that all features, including voice transcription and transaction synchronization, operated as expected. Performance testing of the Boyer-Moore algorithm was conducted on input lengths ranging from 30 to 120 characters. To minimize JVM-related bias, each experiment was repeated 100 times, and the average execution time was calculated. Regression analysis of the results produced the equation y = 1034x + 5192 with a coefficient of determination R² = 0.992. Furthermore, user acceptance testing using the Technology Acceptance Model (TAM) yielded positive results, with average scores above 4.00 on a 5-point scale. These results indicate that integrating IoT and voice-based input significantly improves the efficiency and user acceptance of personal financial management applications.