Open Access. Powered by Scholars. Published by Universities.®
Social and Behavioral Sciences Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Alternative assets (1)
- Asset Allocation (1)
- COVID-19 (1)
- Central bank independence (1)
- Curse of dimensionality (1)
-
- Diversification (1)
- Ed Tech (1)
- Event Study. (1)
- Feature Importance (1)
- Finance (1)
- Inflation (1)
- Investments (1)
- Latin America (1)
- Machine Learning (1)
- Markowitz (1)
- Mean variance (1)
- Monetary policy (1)
- Money supply (1)
- Portfolio (1)
- Portfolio Optimization (1)
- Returns (1)
- Sentiment Analysis (1)
- Shapley Value (1)
- Sneakers (1)
- Stock Prediction (1)
- Twitter Sentiment (1)
Articles 1 - 5 of 5
Full-Text Articles in Social and Behavioral Sciences
Converged Subset Portfolios: An Extension To Subset Optimization, Coleman Cornell
Converged Subset Portfolios: An Extension To Subset Optimization, Coleman Cornell
CMC Senior Theses
The limited span of useful data, coupled with increasingly expansive asset universes, cripples the traditional mean-variance problem. When optimizing in these environments, the pronounced effect of estimation error yields extremely unstable portfolios when evaluated out-of-sample. As a proposed solution to the "curse of dimensionality," Gillen (2016) presents subset optimization as a technique to reduce the impact of estimation error. Instead of optimizing jointly over the entire asset universe, subset optimization na\"ively aggregates over many "subset portfolios" that each optimize over a much smaller random sample of assets. Given the inefficiencies when using naive aggregation, converged subset optimization is presented as …
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 …
Gambling Autonomy: The Impact Of Latin American Central Bank Independence On Risk Aversion Within Monetary Policy Implementation, Julia Duarte Schulman
Gambling Autonomy: The Impact Of Latin American Central Bank Independence On Risk Aversion Within Monetary Policy Implementation, Julia Duarte Schulman
CMC Senior Theses
This paper examines the effect of Latin American central bank independence (CBI) on risk-averse behaviors in monetary policy. Using a fixed effects panel regression, I document how multiple forms of monetary policy are influenced by different macroeconomic variables, conflicting policy targets and central bank independence benchmarks. The results show that increasing CBI has a positive impact on risk aversion, especially in policies targeting inflation and money supply. Additionally, the results show that interest rates and reserve requirements were especially susceptible to changes in independence, while the monetary base and volume of domestic credit were less influenced. Finally, as time and …
Diversifying Investment Portfolios With Collectible Sneakers: Expected Returns And Benefits Of Diversification, Samuel Soo
CMC Senior Theses
This thesis seeks to identify if collectible sneakers can provide diversification benefits to an investor’s portfolio. Using data from a global collectible sneaker marketplace, StockX, I constructed an index to compare it with other traditional assets, including the S&P 500 index and 5-year US Treasury Bills. By calculating key metrics including expected returns, volatility, and correlation, I analyzed the risk-return characteristics of the collectible sneaker asset class compared to other traditional asset classes. From the data analysis I performed, I found that collectible sneakers did not outperform returns significantly compared to traditional asset classes, but had low correlations, which provides …
Zoom In, Class Out: An Event Study On Publicly Traded Ed Tech Firm Valuations During Covid-19, Matiss Ozols
Zoom In, Class Out: An Event Study On Publicly Traded Ed Tech Firm Valuations During Covid-19, Matiss Ozols
CMC Senior Theses
This paper examines how publicly traded Ed Tech firms reacted to negative announcements regarding COVID-19. Using an event study method, I document how an international portfolio of Ed Tech firms react across multiple event windows. The results show that Ed Tech firms reacted positively to the announcement of the first US death and negatively to the World Health Organization’s declaration that COVID-19 was a pandemic. Additionally, differences in geographical location did not impact cumulative abnormal returns across event windows. Finally, firm-specific characteristics such as volatility and financial leverage had little or no significance on stock returns.