Implementing NLP techniques and data for Europe financial market forecasting

Abstract

The large military conflict between Russia and Ukraine has consequences for the global financial market. The European region is one of the hardest hits, which experienced a high energy cost and devaluation of the currency. This paper investigates the Employment Expectations Indicator (EEI) and Economic Sentiment Indicator (ESI) from the business consumer survey index to reflect the reaction of the consumers of the European market by implementing Natural Language Processing (NLP) techniques and machine learning. In the object, the monetary policy decisions from European Central Bank are considered the data set for forecasting the Index. In the result, all nine models from scikit-learn contributed a great job in both categories of Accuracy, Precision, and F-score and Recall with a level of 90% as average. It represents that the NLP techniques effectively forecast the future value of two European business and consumer indexes. However, the limit of the dataset and model mostly related to the performance of NLP techniques is working for forecasting but less related to the expected values of the EEI and ESI indices. Future research would focus more on forecasting the expected value of the two indexes and reflect the consumers' reactions in the markets.