Abstract:

The Consumer Price Index (CPI) is a method that measures the change in the prices of goods and services for household consumption over time. In this study, many independent studies on CPI in the field of artificial intelligence were investigated. As a result of the literature review, it was learned that the use of artificial intelligence in the calculation of CPI is in two processes: "collection and processing of data" and "classification of products". During the data collection and processing process, alternative method studies were carried out by the official statistics offices to the data collection process by means of questionnaires. For this purpose, product information and prices on online shopping sites have been compiled using methods such as web crawling technique. In the process of classification of products, various machine learning methods were used to match the product information obtained from companies in digital environment with the classification methods used within the scope of CPI. For this, natural language processing methods have been applied to digitize text bases data. As a result, with this study, studies using artificial intelligence within the scope of CPI were gathered under a single roof and a prediction was created for new alternative calculation methods.

Keywords: