Extended CV

This page expands on the CV: what each course actually covered and the competencies it builds. My degree is a Master in Business Administration with a major in Business Analytics (siviløkonom). I have a particular interest in machine learning, applied forecasting, and turning data into insight, reflected in the courses below and in my master’s thesis.

Master’s thesis

A Comparison of Fundamental and Statistical Risk Factor Models

MØLBA4900 · 2026

Joint master’s thesis, carried out with a project partner. We built and evaluated a fundamental (characteristic-based, Barra-style) multi-factor risk model against a statistical (PCA-based) factor model for covariance estimation and global minimum-variance (GMV) portfolio construction on the Oslo Stock Exchange, benchmarked against a naive estimator. The work spanned the full pipeline, from raw data to out-of-sample statistical testing.

Data universe and cleaning (Python, EODHD API).

• Collected unadjusted and adjusted close prices for listed and delisted companies to mitigate survivorship bias, using unadjusted prices for feature construction (adjusted prices embed look-ahead bias from future corporate actions) and adjusted prices for returns.
• Cleaned the universe: detected and resolved renamed/duplicate tickers via excessive-correlation checks, flagged and dropped corrupt price series and unexplained outliers, and documented every removed ticker with a reason.
• Handled currency consistently: identified time-series and reporting currencies, manually verified missing balance-sheet currencies against published reports, and mapped historical FX pairs to convert everything to NOK.

Factor construction (point-in-time).

• Built around eleven firm characteristics with point-in-time arrival of accounting information: value (book-to-market), size (log market cap), momentum, short-term reversal, CAPM idiosyncratic volatility, Amihud illiquidity, dividend yield, market beta, oil-price beta (Brent futures), interest-rate / yield-spread sensitivity, leverage (debt-to-assets), and asset growth, plus GICS sector mapping.

Estimation and diagnostics (R).

• Estimated the fundamental model as a sequence of market-cap-weighted cross-sectional WLS regressions (one per trading day) to recover factor returns, with per-cross-section winsorization, and formed the covariance as \(B\,\Sigma_f\,B' + D\) with EWMA-smoothed idiosyncratic variance.
• Ran diagnostics: factor-return series, average \(R^2\), variance-inflation (VIF) checks for multicollinearity, and ADF stationarity tests.
• Estimated the statistical model by EWMA-weighted rolling PCA, with the number of factors chosen by Bai–Ng information criteria.

Out-of-sample evaluation.

• Constructed predicted GMV portfolios from each model’s covariance in a walk-forward design, tracked realised variance, and tested loss differentials with the Diebold–Mariano test (including a stationarity check on the differentials).
• Result: the two model families were statistically indistinguishable over the full out-of-sample period — interpreted, in light of the estimation-error literature, as a substantive finding about a small market rather than a non-result.

Quantitative and technical courses

Financial modelling

MØLBA3005 · A

Portfolio theory and risk diversification; empirical tests of the Efficient Market Hypothesis and CAPM; capital structure and the optimal financing mix; valuation principles and practice; forwards, futures and options; and modelling of volatility and correlation — implied and realised volatility, and volatility forecasting with ARCH, GARCH, HAR-RV and quantile regression. Develops the ability to price derivatives under the no-arbitrage principle, apply Monte Carlo simulation to option pricing, measure portfolio risk with several approaches, value firms and equity, and implement trading strategies.

Quantitative methods & advanced statistical modelling

LMSM130 (A) · MØLBA3007 (B)

A two-course econometrics sequence: research design and the assumptions and interpretation of multiple linear regression; logistic regression; instrumental-variables regression; panel-data models; exploratory and confirmatory factor analysis; and, at the advanced level, endogeneity, models for limited dependent variables, and partial least squares structural equation modelling (PLS-SEM). Develops the ability to test OLS assumptions, distinguish predictive from causal interpretations, justify a methodology from its underlying assumptions, and design and run advanced empirical studies on business, economic and financial data.

Machine learning

MØLBA3002 · B

Supervised learning framed around minimising expected loss for optimal decisions: regression methods (linear regression, neural networks); classification (logistic regression, discriminant analysis, naive Bayes); performance evaluation; the bias–variance trade-off; model selection and averaging; regularization; and cross-validation and the bootstrap. Develops the ability to implement and evaluate machine-learning algorithms and to make qualified method choices for a given problem.

Business forecasting

MØLBA3004 · A

Time-series data patterns and decomposition into trend, cycle, season and noise; moving averages and exponential smoothing; dynamic regression; ARIMA; multivariate time series such as vector autoregression; advanced methods including neural networks and state-space models; forecast combination; and loss functions, forecast accuracy and optimality. Develops the ability to generate and evaluate forecasts, combine them to improve accuracy, and recognise the conditions under which models break.

Applied programming

LDBA200 · A

Core programming concepts; variable types and data structures; functions, loops, assignments, subsetting and conditionals; algorithmic thinking; tooling for data wrangling, descriptive analysis, testing and visualization; debugging; and documentation, reproducibility and automation. Develops the ability to write programs that solve business problems and to produce reproducible scripts and dynamic reports.

Data engineering

MØLBA3001 · B

Capturing, cleaning, transforming and loading data: data types, structures and sources; data acquisition; storage in databases and data warehouses; SQL; cloud solutions and programming interfaces; the peculiarities of Big Data; and the role of data management in creating business value. Develops the ability to extract, transform and merge data with SQL and to access local and web-based sources.

Business performance / efficiency analysis

MØLBA3003 · B

Measuring and benchmarking firm performance: identifying inputs and outputs; using determinants and environmental variables to capture heterogeneity between firms; efficiency analysis with both parametric and non-parametric methods; optimization methods; productivity analysis and indices; and benchmarking. Develops the ability to conduct productivity and efficiency analyses and to recommend actions to improve performance.

Data protection and ethics

MØLBA3008 · C

Privacy and data protection; the GDPR and privacy by design; data classification and transfer; the EEA obligations and rules on cross-border data transfer; and the ethical paradoxes of big-data analytics. Develops the ability to identify privacy and legal risks and to manage data within regulation and ethical standards.

Management and business courses

Management accounting and control

LMØS120 · C

Traditional and modern approaches to management accounting and the link between strategy and financial management; budgets, forecasts, residual income models, the balanced scorecard, activity-based costing and cost targeting; performance measurement and management; and the changing role of the control function under digitalization.

Strategy and leadership

LMMF120 · B

Strategy as an academic field and strategic processes; the digital influence on strategy; market and competition positioning; the leadership role and digital transformation; competitor and environmental analysis; network strategies; incentive systems and performance metrics; and ethics and social responsibility.

Sustainable business model innovation

INN3024 · C

Designing business models that align economic, social and environmental goal attainment; analysing business models and corporate responsibility through case studies of Norwegian and international firms; and moving beyond the traditional responsibility–profitability trade-off.