Linear Predictive Coding vs. Kalman Filter for Urban Finance Prediction in Smart Cities with S &P/BMV IPC

This paper presents a comparison between two prediction methods, Linear Predictive Coding (LPC) and Kalman Filter (KF), in the context of Smart Cities. The research uses historical data from one of the financial index in Mexico: the S &P/BMV IPC Index, a crucial indicator that reflects the performance of the Mexican stock market. The main objective of this study is to evaluate the effectiveness of these prediction methods to improve financial management and decision-making in smart urban environments. To carry out this comparison, some factors are taken into consideration, such as the accuracy of the predictions, their error, and the ability to adapt to changes in the market. The results show that both methods have advantages and disadvantages but can be highly useful in different academic and financial contexts, as in both cases relative errors below 4% were achieved; however, the KF method exhibited even lower mean squared errors than the LPC method. This contributes to the field of urban finance, providing decision-makers and investors with a deeper understanding of these two tools available for prediction. In addition, the results can be considered for efficient and sustainable economic management in a world increasingly focused on digital transformation and resource optimization in smart cities.