Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Adaptive (1)
- Agricultural justice (1)
- Feature Importance (1)
- Food ethics (1)
- Food justice (1)
-
- Game Theory (1)
- Industrial agriculture (1)
- Information Aggregation (1)
- Machine Learning (1)
- Market fundamentalism (1)
- Nonparametric (1)
- Regression (1)
- Residual (1)
- Sentiment Analysis (1)
- Shapley Value (1)
- Social Psychology (1)
- Spline (1)
- Stock Prediction (1)
- Structural (1)
- Sustainability (1)
- Twitter Sentiment (1)
- Utility Maximisation (1)
Articles 1 - 4 of 4
Full-Text Articles in Physical Sciences and Mathematics
Feature Investigation For Stock Returns Prediction Using Xgboost And Deep Learning Sentiment Classification, Seungho (Samuel) Lee
Feature Investigation For Stock Returns Prediction Using Xgboost And Deep Learning Sentiment Classification, Seungho (Samuel) Lee
CMC Senior Theses
This paper attempts to quantify predictive power of social media sentiment and financial data in stock prediction by utilizing a comprehensive set of stock-related fundamental and technical variables and social media sentiments. For conducting sentiment analysis, this study employs a pretrained finBERT model that provides three different sentiment classifications and respective softmax scores. Hence, the significance of these variables is evaluated with XGBoost regression and Shapley Additive exPlanations (SHAP) frameworks. Through investigating feature importance, this study finds that statistical properties of sentiment variables provide a stronger predictive power than a weighted sentiment score and that it is possible to quantify …
An Evaluation Of Knot Placement Strategies For Spline Regression, William Klein
An Evaluation Of Knot Placement Strategies For Spline Regression, William Klein
CMC Senior Theses
Regression splines have an established value for producing quality fit at a relatively low-degree polynomial. This paper explores the implications of adopting new methods for knot selection in tandem with established methodology from the current literature. Structural features of generated datasets, as well as residuals collected from sequential iterative models are used to augment the equidistant knot selection process. From analyzing a simulated dataset and an application onto the Racial Animus dataset, I find that a B-spline basis paired with equally-spaced knots remains the best choice when data are evenly distributed, even when structural features of a dataset are known …
Factory To Table: A Philosophic Analysis Of The Justice Or Lack Thereof Of Agricultural Markets, Will Carter
Factory To Table: A Philosophic Analysis Of The Justice Or Lack Thereof Of Agricultural Markets, Will Carter
CMC Senior Theses
How food is produced has dramatic consequences on how we live, our world’s justice, and the future of our planet. In a world increasingly driven by neoliberalism, agricultural markets have been incentivized to industrialize, globalize, and consolidate. This has resulted in the global dominance of a new type of agriculture, industrial agriculture, driven by the market logic of lowering costs and raising profits. Industrial agriculture has undoubtedly generated the profound benefit of cheaper, more plentiful food in much of the world. These favorable innovations lead many scholars to argue that free markets produce the most just and efficient arrangements for …
Information Prioritization: A Comparison Between Utility Maximizers And Probability Matchers, Yusuf Ismaeel
Information Prioritization: A Comparison Between Utility Maximizers And Probability Matchers, Yusuf Ismaeel
CMC Senior Theses
This thesis examines the differences between probability matchers and utility maximizers in their preferences for information sources in a lab environment. In this paper, we consider the best source of information to be the most connected one. We conducted several linear probability model type regressions along with logit regressions. Furthermore, we also attempted to control and fix any potential misclassifications in classifying the cognitive strategy by using instrumental variables. The results show that utility maximizers will almost always choose the most informed node. Probability matchers, on the other hand, do not exhibit such a behavior as the probability matching strategy …