The objective of this thesis is to identify the most effective variables and the optimal sequences for their input, in order to make the AI more accurate and efficient while minimizing data misinterpretations, within the framework of DuPont analysis for evaluating business performance. This experiment is repeated across different types of AI to assess potential differences and determine which models are the most effective. A subsequent analysis will examine the financial tone, word frequency, and the degree of optimism or pessimism used by the various artificial intelligence systems.

The objective of this thesis is to identify the most effective variables and the optimal sequences for their input, in order to make the AI more accurate and efficient while minimizing data misinterpretations, within the framework of DuPont analysis for evaluating business performance. This experiment is repeated across different types of AI to assess potential differences and determine which models are the most effective. A subsequent analysis will examine the financial tone, word frequency, and the degree of optimism or pessimism used by the various artificial intelligence systems.

Asking right, reading tone: a DuPont experiment on Artificial Intelligence's performance.

CRESTALE, GIOVANNI
2024/2025

Abstract

The objective of this thesis is to identify the most effective variables and the optimal sequences for their input, in order to make the AI more accurate and efficient while minimizing data misinterpretations, within the framework of DuPont analysis for evaluating business performance. This experiment is repeated across different types of AI to assess potential differences and determine which models are the most effective. A subsequent analysis will examine the financial tone, word frequency, and the degree of optimism or pessimism used by the various artificial intelligence systems.
2024
Asking right, reading tone: a DuPont experiment on Artificial Intelligence's performance.
The objective of this thesis is to identify the most effective variables and the optimal sequences for their input, in order to make the AI more accurate and efficient while minimizing data misinterpretations, within the framework of DuPont analysis for evaluating business performance. This experiment is repeated across different types of AI to assess potential differences and determine which models are the most effective. A subsequent analysis will examine the financial tone, word frequency, and the degree of optimism or pessimism used by the various artificial intelligence systems.
DuPont
AI
Tone
File in questo prodotto:
File Dimensione Formato  
Crestale_Giovanni.pdf

accesso aperto

Dimensione 2.32 MB
Formato Adobe PDF
2.32 MB Adobe PDF Visualizza/Apri

The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12608/93521