Mining News Data for the Measurement and Prediction of Inflation Expectations
| Autor: | Diana Gabrielyan, Jaan Masso, Lenno Uusküla |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Topic model
Inflation Index (economics) Qca business.industry Computer science media_common.quotation_subject Headline inflation Natural language processing Big data Web data Inflation expectations Conference Pls Autoregressive model Quantitative analysis (finance) Sem News data Econometrics business Topic modelling media_common Internet data |
| Zdroj: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia instname Contributions to Statistics ISBN: 9783030562182 |
| Popis: | [EN] In this paper we use high frequency multidimensional textual news data and propose an index of inflation news. We utilize the power of text mining and its ability to convert large collections of text from unstructured to structured form for in-depth quantitative analysis of online news data. The significant relationship between the household’s infla-tion expectations and news topics is documented and the forecasting performance of news-based indices is evaluated for different horizons and model variations. Results sug-gest that with optimal number of topics a machine learning model is able to forecast the inflation expectations with greater accuracy than the simple autoregressive models. Addi-tional results from forecasting headline inflation indicate that the overall forecasting accu-racy is at a good level. Findings in this paper support the view in the literature that the news are good indicators of inflation and are able to capture inflation expectations well. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|