Categories

A generated topic index built from published post metadata.

1 Quantitative Finance

Volatility Forecasts (Part 5 — PGARCH) (2026-03-10): Part 5 revisits the three-feature PGARCH stage: with only fast return features, a dynamic long-run anchor is hard to interpret, so the cleaner specification keeps mu constant and lets persistence and shock loading adapt.
Volatility Forecasts (Part 4 — RMSE Benchmarks and QLIKE Training) (2026-03-03): We keep RMSE for benchmark comparability, then refit STES and XGBSTES under QLIKE to see how the training loss changes out-of-sample ranking and calibration.
Expected Performance of a Mean-Reversion Trading Strategy — Part 4 (2026-03-03): How does parameter estimation error affect the Sharpe ratio of a mean-reversion strategy?
Expected Performance of a Mean-Reversion Trading Strategy - Part 3 (2026-03-02): How does a correlated bias in the fair-value estimate affect the Sharpe ratio of a mean-reversion strategy?
Expected Performance of a Mean-Reversion Trading Strategy - Part 2 (2026-03-01): What happens to the performance of a mean-reversion strategy when the fair value is estimated with a constant bias?
Graph-Regularized Low-Rank Models (Part 1: JGB Curve) (2026-02-14)
Signature Methods (Part 4 — Rolling Signatures in Volatility Forecasts) (2026-02-06): We augment STES and XGBoost-STES volatility models with rolling signature features computed from SPY return paths. After careful feature selection, regularization tuning, and multi-channel augmentation, we conclude that the results are negative but instructive.
Volatility Forecasts (Part 3 - XGBSTES Algorithm 2) (2026-01-24): We extend STES by replacing its linear component with XGBoost, then dig into why RMSE can underperform and propose a more stable end-to-end fitting algorithm.
Signature Methods (Part 3 - Lead–Lag Augmentation and Practical Limitations to the Signature Method) (2025-12-25): Continuing from the previous post, we work through three examples of approximating path functionals using linear functionals of truncated signatures in increasingly less practical way to illustrate…
Signature Methods (Part 2 - Signature and Augmentation) (2025-12-21): Previously I provided some motivations for the use of signatures.
Signature Methods (Part 1 - Motivation) (2025-12-14): I am starting a series on the signature method now that I have some free time on my hands over the 2025 holiday season.
Short Rate Models (Part 4: Simulating and Calibrating the Vasicek Model) (2024-09-16): In our previous post, we introduced the Vasicek model that used the Ornstein-Uhlenbeck (OU) process to model the dynamics of the short rates.
Short Rate Models (Part 3: Introducing Vasicek Model) (2024-08-10): We continue our refresher series on the short-rate models. In the previous post, I introduced the Merton model and the Euler-Maruyama method to simulate it.
Volatility Forecasts (Part 2 - XGBSTES Algorithm 1) (2024-07-18): In the previous post, we replicated the Smooth Transition Exponential Smoothing (STES) model from (Taylor 2004) and (Liu, Taylor, Choo 2020).
Short Rate Models (Part 2: Simulating and Calibrating the Merton Model) (2024-05-19): Let us continue our refresher series on short-rate models. We introduced the Merton short rate model in the previous post.
Short Rate Models (Part 1: Introducing Merton’s Model) (2024-05-10): Welcome to my refresher series on short-rate models, dear reader! These mathematical marvels are not just academic curiosities but crucial tools in finance.
Expected Performance of a Mean-Reversion Trading Strategy - Part 1 (2022-09-01): A value strategy posits that the worth of an asset tends to oscillate around a more gradual, underlying trend.
Volatility Forecasts (Part 1 - STES Model) (2021-09-07): Exponential smoothing (ES) is a simple yet widely used approach to volatility forecasting in finance and economics.

2 Volatility Modeling

Volatility Forecasts (Part 5 — PGARCH) (2026-03-10): Part 5 revisits the three-feature PGARCH stage: with only fast return features, a dynamic long-run anchor is hard to interpret, so the cleaner specification keeps mu constant and lets persistence and shock loading adapt.
Volatility Forecasts (Part 4 — RMSE Benchmarks and QLIKE Training) (2026-03-03): We keep RMSE for benchmark comparability, then refit STES and XGBSTES under QLIKE to see how the training loss changes out-of-sample ranking and calibration.
Signature Methods (Part 4 — Rolling Signatures in Volatility Forecasts) (2026-02-06): We augment STES and XGBoost-STES volatility models with rolling signature features computed from SPY return paths. After careful feature selection, regularization tuning, and multi-channel augmentation, we conclude that the results are negative but instructive.
Volatility Forecasts (Part 3 - XGBSTES Algorithm 2) (2026-01-24): We extend STES by replacing its linear component with XGBoost, then dig into why RMSE can underperform and propose a more stable end-to-end fitting algorithm.
Volatility Forecasts (Part 2 - XGBSTES Algorithm 1) (2024-07-18): In the previous post, we replicated the Smooth Transition Exponential Smoothing (STES) model from (Taylor 2004) and (Liu, Taylor, Choo 2020).
Volatility Forecasts (Part 1 - STES Model) (2021-09-07): Exponential smoothing (ES) is a simple yet widely used approach to volatility forecasting in finance and economics.

3 Time Series

Volatility Forecasts (Part 5 — PGARCH) (2026-03-10): Part 5 revisits the three-feature PGARCH stage: with only fast return features, a dynamic long-run anchor is hard to interpret, so the cleaner specification keeps mu constant and lets persistence and shock loading adapt.
Forecasts Comparison (2026-03-04): An introduction to the statistical tools for comparing forecast accuracy — the Diebold-Mariano test, the role of the loss function, and the Mincer-Zarnowitz regression as a calibration diagnostic.
Volatility Forecasts (Part 4 — RMSE Benchmarks and QLIKE Training) (2026-03-03): We keep RMSE for benchmark comparability, then refit STES and XGBSTES under QLIKE to see how the training loss changes out-of-sample ranking and calibration.
Signature Methods (Part 4 — Rolling Signatures in Volatility Forecasts) (2026-02-06): We augment STES and XGBoost-STES volatility models with rolling signature features computed from SPY return paths. After careful feature selection, regularization tuning, and multi-channel augmentation, we conclude that the results are negative but instructive.
Volatility Forecasts (Part 3 - XGBSTES Algorithm 2) (2026-01-24): We extend STES by replacing its linear component with XGBoost, then dig into why RMSE can underperform and propose a more stable end-to-end fitting algorithm.
Signature Methods (Part 3 - Lead–Lag Augmentation and Practical Limitations to the Signature Method) (2025-12-25): Continuing from the previous post, we work through three examples of approximating path functionals using linear functionals of truncated signatures in increasingly less practical way to illustrate…
Signature Methods (Part 2 - Signature and Augmentation) (2025-12-21): Previously I provided some motivations for the use of signatures.
Signature Methods (Part 1 - Motivation) (2025-12-14): I am starting a series on the signature method now that I have some free time on my hands over the 2025 holiday season.
Volatility Forecasts (Part 2 - XGBSTES Algorithm 1) (2024-07-18): In the previous post, we replicated the Smooth Transition Exponential Smoothing (STES) model from (Taylor 2004) and (Liu, Taylor, Choo 2020).
Volatility Forecasts (Part 1 - STES Model) (2021-09-07): Exponential smoothing (ES) is a simple yet widely used approach to volatility forecasting in finance and economics.

4 Interest Rate Models

Short Rate Models (Part 4: Simulating and Calibrating the Vasicek Model) (2024-09-16): In our previous post, we introduced the Vasicek model that used the Ornstein-Uhlenbeck (OU) process to model the dynamics of the short rates.
Short Rate Models (Part 3: Introducing Vasicek Model) (2024-08-10): We continue our refresher series on the short-rate models. In the previous post, I introduced the Merton model and the Euler-Maruyama method to simulate it.
Short Rate Models (Part 2: Simulating and Calibrating the Merton Model) (2024-05-19): Let us continue our refresher series on short-rate models. We introduced the Merton short rate model in the previous post.
Short Rate Models (Part 1: Introducing Merton’s Model) (2024-05-10): Welcome to my refresher series on short-rate models, dear reader! These mathematical marvels are not just academic curiosities but crucial tools in finance.

5 Stochastic Processes

Expected Performance of a Mean-Reversion Trading Strategy — Part 4 (2026-03-03): How does parameter estimation error affect the Sharpe ratio of a mean-reversion strategy?
Expected Performance of a Mean-Reversion Trading Strategy - Part 3 (2026-03-02): How does a correlated bias in the fair-value estimate affect the Sharpe ratio of a mean-reversion strategy?
Expected Performance of a Mean-Reversion Trading Strategy - Part 2 (2026-03-01): What happens to the performance of a mean-reversion strategy when the fair value is estimated with a constant bias?
Short Rate Models (Part 4: Simulating and Calibrating the Vasicek Model) (2024-09-16): In our previous post, we introduced the Vasicek model that used the Ornstein-Uhlenbeck (OU) process to model the dynamics of the short rates.
Short Rate Models (Part 3: Introducing Vasicek Model) (2024-08-10): We continue our refresher series on the short-rate models. In the previous post, I introduced the Merton model and the Euler-Maruyama method to simulate it.
Short Rate Models (Part 2: Simulating and Calibrating the Merton Model) (2024-05-19): Let us continue our refresher series on short-rate models. We introduced the Merton short rate model in the previous post.
Short Rate Models (Part 1: Introducing Merton’s Model) (2024-05-10): Welcome to my refresher series on short-rate models, dear reader! These mathematical marvels are not just academic curiosities but crucial tools in finance.
Expected Performance of a Mean-Reversion Trading Strategy - Part 1 (2022-09-01): A value strategy posits that the worth of an asset tends to oscillate around a more gradual, underlying trend.

6 Signature Methods

Signature Methods (Part 4 — Rolling Signatures in Volatility Forecasts) (2026-02-06): We augment STES and XGBoost-STES volatility models with rolling signature features computed from SPY return paths. After careful feature selection, regularization tuning, and multi-channel augmentation, we conclude that the results are negative but instructive.
Signature Methods (Part 3 - Lead–Lag Augmentation and Practical Limitations to the Signature Method) (2025-12-25): Continuing from the previous post, we work through three examples of approximating path functionals using linear functionals of truncated signatures in increasingly less practical way to illustrate…
Signature Methods (Part 2 - Signature and Augmentation) (2025-12-21): Previously I provided some motivations for the use of signatures.
Signature Methods (Part 1 - Motivation) (2025-12-14): I am starting a series on the signature method now that I have some free time on my hands over the 2025 holiday season.

7 Trading Strategies

Expected Performance of a Mean-Reversion Trading Strategy — Part 4 (2026-03-03): How does parameter estimation error affect the Sharpe ratio of a mean-reversion strategy?
Expected Performance of a Mean-Reversion Trading Strategy - Part 3 (2026-03-02): How does a correlated bias in the fair-value estimate affect the Sharpe ratio of a mean-reversion strategy?
Expected Performance of a Mean-Reversion Trading Strategy - Part 2 (2026-03-01): What happens to the performance of a mean-reversion strategy when the fair value is estimated with a constant bias?
Expected Performance of a Mean-Reversion Trading Strategy - Part 1 (2022-09-01): A value strategy posits that the worth of an asset tends to oscillate around a more gradual, underlying trend.

8 Machine Learning

Malaria Detection (Part 4: Finetuning VGG16 with LoRA) (2024-08-20): In the previous post, we built a finetuned VGG16-based model (Model 4) to detect malaria from cell images.
Malaria Detection (Part 3: Results and Reflections) (2024-07-17): I was honestly amazed by these results. Even the base model achieved 98% accuracy! However, accuracy isn’t everything. Let’s break down what these numbers really mean.
Malaria Detection (Part 2: Model Building and Training) (2024-06-13): In the previous post of this series, we introduced the problem of Malaria detection and prepared and preprocessed our dataset.
Malaria Detection (Part 1: Introduction and Data Preparation) (2024-06-12): I recently learned more about convolutional neural networks (CNNs) and how they are used to analyze images.

9 Computer Vision

Malaria Detection (Part 4: Finetuning VGG16 with LoRA) (2024-08-20): In the previous post, we built a finetuned VGG16-based model (Model 4) to detect malaria from cell images.
Malaria Detection (Part 3: Results and Reflections) (2024-07-17): I was honestly amazed by these results. Even the base model achieved 98% accuracy! However, accuracy isn’t everything. Let’s break down what these numbers really mean.
Malaria Detection (Part 2: Model Building and Training) (2024-06-13): In the previous post of this series, we introduced the problem of Malaria detection and prepared and preprocessed our dataset.
Malaria Detection (Part 1: Introduction and Data Preparation) (2024-06-12): I recently learned more about convolutional neural networks (CNNs) and how they are used to analyze images.

10 Deep Learning

Malaria Detection (Part 4: Finetuning VGG16 with LoRA) (2024-08-20): In the previous post, we built a finetuned VGG16-based model (Model 4) to detect malaria from cell images.
Malaria Detection (Part 3: Results and Reflections) (2024-07-17): I was honestly amazed by these results. Even the base model achieved 98% accuracy! However, accuracy isn’t everything. Let’s break down what these numbers really mean.
Malaria Detection (Part 2: Model Building and Training) (2024-06-13): In the previous post of this series, we introduced the problem of Malaria detection and prepared and preprocessed our dataset.
Malaria Detection (Part 1: Introduction and Data Preparation) (2024-06-12): I recently learned more about convolutional neural networks (CNNs) and how they are used to analyze images.

11 Healthcare AI

Malaria Detection (Part 4: Finetuning VGG16 with LoRA) (2024-08-20): In the previous post, we built a finetuned VGG16-based model (Model 4) to detect malaria from cell images.
Malaria Detection (Part 3: Results and Reflections) (2024-07-17): I was honestly amazed by these results. Even the base model achieved 98% accuracy! However, accuracy isn’t everything. Let’s break down what these numbers really mean.
Malaria Detection (Part 2: Model Building and Training) (2024-06-13): In the previous post of this series, we introduced the problem of Malaria detection and prepared and preprocessed our dataset.
Malaria Detection (Part 1: Introduction and Data Preparation) (2024-06-12): I recently learned more about convolutional neural networks (CNNs) and how they are used to analyze images.

12 Statistics

Intercept Invariance to Added Standardized Features (2026-02-10): When centering (or standardizing) features leaves the intercept unchanged, and when it does not.

13 Linear Models

Intercept Invariance to Added Standardized Features (2026-02-10): When centering (or standardizing) features leaves the intercept unchanged, and when it does not.

14 Optimization

Intercept Invariance to Added Standardized Features (2026-02-10): When centering (or standardizing) features leaves the intercept unchanged, and when it does not.

15 Rates

Graph-Regularized Low-Rank Models (Part 1: JGB Curve) (2026-02-14)

16 Dimensionality Reduction

Graph-Regularized Low-Rank Models (Part 1: JGB Curve) (2026-02-14)

17 Regularization

Graph-Regularized Low-Rank Models (Part 1: JGB Curve) (2026-02-14)

18 Econometrics

Forecasts Comparison (2026-03-04): An introduction to the statistical tools for comparing forecast accuracy — the Diebold-Mariano test, the role of the loss function, and the Mincer-Zarnowitz regression as a calibration diagnostic.

19 Forecasting

Forecasts Comparison (2026-03-04): An introduction to the statistical tools for comparing forecast accuracy — the Diebold-Mariano test, the role of the loss function, and the Mincer-Zarnowitz regression as a calibration diagnostic.