Challenge
The study examined whether financial fundamentals could statistically explain company market capitalisation while remaining interpretable enough to support meaningful conclusions.
Case study09 / 09
What explains market value?
An equity-valuation study comparing interpretable regression with regularized models across the Stockholm Stock Exchange.
Engagement
KTH · B.Sc. thesis
Role
Researcher and co-author
Year
2023
1,440
company-year observations analysed
My contribution
With a co-author, I built and tested OLS, Ridge, LASSO and Elastic Net models using Bloomberg data from 181 OMXSGI companies between 2010 and 2019.
Outcome
LASSO achieved the lowest prediction error, while the reduced OLS model was selected for interpretation and achieved a holdout MSE of 0.387.
Approach
Approach
- 01
Prepared and log-transformed the dataset, winsorizing observations at the first and ninety-ninth percentiles.
- 02
Tested heteroskedasticity and multicollinearity using Breusch-Pagan, robust standard errors and VIF diagnostics.
- 03
Compared regularized models with a reduced OLS specification, balancing predictive fit against interpretability.
Cleaned Bloomberg datasetOLS regression modelRegularized model comparisonAcademic thesis
