EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

3798. Applying multiple indicators to assess the relationship between finance and human factors

Invited abstract in session WA-6: Advancements of OR-analytics in statistics, machine learning and data science 16, stream Advancements of OR-analytics in statistics, machine learning and data science.

Wednesday, 8:30-10:00
Room: 1013 (building: 202)

Authors (first author is the speaker)

1. Betül Kalaycı
Financial Mathematics, Institute of Applied Mathematics

Abstract

There are various empirical phenomena relating to individual investors' behavior, such as how their emotions and opinions influence their choices. Sentiment refers to all of these emotions and opinions. In finance, stochastic changes can occur in response to investor sentiment levels. Machine Learning methods are well-known and helpful tools for prediction problems, and they have already been applied successfully to handle a wide range of financial problems. In this study, we focus on the behavior of financial difficulties based on the sentiment levels of investors, rather than pure financial problems. The goal of this study is to evaluate sentiment index prediction performance using two-stage MARS-NN, MARS-RF, RF-MARS, RF-NN, NN-MARS, and NN-RF hybrid models. We further prepare to describe people's sentiments toward the economy according to their level of confidence. For this objective, we employ HMM to estimate the underlying state change of the Consumer Confidence Index (CCI) and investigate its relationship with some macroeconomic indices (CPI, GDP, and currency rate) at monthly intervals. The purpose is to monitor and comprehend the transitions between these phases, as well as to chart a course through them. We also plan to apply volatility models to each subgroup we receive in HMM to see if we can improve our predicting results.

Keywords

Status: accepted

Back to the list of papers