[October 2024] Curriculum Vitae. my long-form resume

tags: dustin lennon, applied scientist, statistician

[October 2024] Resume. an adaptive granularity resume

tags: dustin lennon, applied scientist, statistician

[February 2021] Personalized Point Processes: A Simple Bayesian Analysis. This post describes a homogeneous Poisson process using a Gamma conjugate prior that can be used to estimate a pooled, per-subject intensity given a collection of realizations.

tags: point process, bayesian, multiple realizations

[February 2021] Doubly and Randomly Censored Data. A derivation of the density functions and likelihood expression associated with doubly and randomly censored data.

tags: censored data, likelihood, distribution, derivation, event data

[September 2018] Probability Integral Transform, A Proof. This post elucidates the connection between the generalized inverse, the cdf, the quantile function, and the uniform distribution.

tags: statistics, theory, probability integral transform, proof

[September 2016] Adaptive Rejection Sampling. This post describes and implements an adaptive rejection sampler for log-concave densities.

tags: adaptive sampling, rejection sampling, logconcave density, distribution

[November 2012] Probabilistic Performance Guarantees for Oversubscribed Resources. This paper constructs a model for shared resource utilization, determines stochastic bounds for resource exhaustion, and simulates results.

tags: simulation, stochastic resource allocation

[December 2023] Command Line QR Codes. A simple python script to generate a QR code from a URL

[April 2021] Numerical Linear Algebra: Householder a'la Golub and Van Loan. Exploring properties of Householder transformations

tags: numerical linear algebra, householder

[April 2021] pydlennon: pandas extensions. An extension of the pandas categorical dtype that better encapsulates metadata

tags: pandas, extension, categorical data, metadata

[October 2019] pytrope: psycopg2 extensions. This notebook introduces the pytrope.psycopg2_extras package.

tags: python, matplotlib, pytrope, helper methods

[October 2019] pytrope: matplotlib extensions. This notebook introduces the pytrope.matplotlib_extras package.

tags: python, matplotlib, pytrope, helper methods

[December 2020] Cash Flow Considerations for Machine Learning. An analysis of early LendingClub data, focused on default rates for various load traunches. Note that this is packaged as a reveal.js slideshow.

tags: cash flow, loans, survival analysis, logrank statistic, machine learning, lending club

[March 2021] Reproducing Results: ARM, Chapter 4. This notebook reproduces tables and figures in ARM, Chapter 4 [GH07]

tags: statsmodels, reproducible, regression

[February 2021] Reproducing Results: ARM, Chapter 3. This notebook reproduces tables and figures in ARM, Chapter 3 [GH07]

tags: statsmodels, reproducible, regression

[September 2019] A Bayesian Hello World. Using the (a) statsmodels and (b) pystan packages, this notebook reproduces simple regression results in ARM, Section 3.1 [GH07]

tags: statsmodels, pystan, linear regression, bayesian analysis, non-informative priors

[October 2015] Uber Interview Challenge. My take on an Uber data-science assignment.

tags: uber, pre-interview, homework

[October 2013] Optimal Lending Club Portfolios. The paper characterizes an optimal, managed portfolio with annual returns in excess of 12%.

tags: lending club, optimal portfolios, survival random forest, machine learning

[August 2019] Unlocking TrueType Fonts: Fontforge, Matplotlib, and Partially Ordered Occlusions. This post shows how to merge ttf files and manipulate truetype glyphs.

tags: python, fontforge, matplotlib, shapely

[August 2019] Published Pages Cheatsheet. This page catalogs the features available on the Published Pages framework.

tags: publishing, framework, feature overview

[July 2019] Recommendation Systems, A Mathematical Overview. This post provides an overview of recommendation systems and algorithms.

tags: machine learning, recommendation systems, algorithms

[July 2019] Recommending a Data Warehouse. This webpage gives an overview of Gartner's 2019 'critical capabilities' analysis and showcases a webtool that provides personalized recommendations.

tags: data warehouse, planning, personalization, gartner

[August 2015] Namecheap, Dynamic IP Addresses, and Hosting Multiple Sites. This post shows how to augment Namecheap's ddclient script to support multiple hosts on a dynamic IP.

tags: namecheap, ddclient, dynamic ip address, multiple sites

[March 2021] Annotations: Elements of Statistical Learning. My margin notes from reading Hastie, Tibshirani, and Friedman

tags: notes, elements of statistical learning, machine learning