| dc.description.abstract | Asset valuation is often subjective and can vary between appraisers, leading to uncertainty in determining an accurate value. The high volatility of certain asset types further complicates the effort to establish a stable and reliable valuation. The application of machine learning techniques, particularly the Naive Bayes algorithm, can help improve accuracy in asset valuation. By involving historical data, including the value of pledged assets, market data, and industry trends, machine learning enables pawnshops to generate more precise and objective estimates. The Naive Bayes algorithm, which uses probability and statistics to predict asset values, can efficiently process data and generate more accurate predictions. This study aims to explore the application of machine learning in determining the value of pledged assets, such as jewelry, electronics, or vehicles, using the Naive Bayes Classifier model. This method can identify hidden patterns within historical data, making it easier to predict asset prices or values more accurately. In this context, the study proposes a formula for stable and accurate asset valuation, which can reduce errors in pawn transactions caused by subjective appraisals. The application of this machine learning model is expected to enhance the efficiency and reliability of asset valuation processes in pawnshops, benefiting both debtors and stakeholders by determining more fair and accurate asset values. | en_US |
