Data Science & Analytics
Context & Philosophy
I come at this from data science and software engineering training, plus years of machine-learning and data-engineering work. Data science, analytics, and statistics are close cousins of mathematics, more specific in application than the mathematics and computer science on the Quantum & Computer Science page. This page is where that applied side lives: data engineering, analytics, and the NLP and machine-learning work below.
Machine learning and statistical learning are the foundations under NLP, large language models, and generative AI, and that is how I think they are best understood and used: as tools built from fundamentals you can actually follow, judged on their methods and evidence rather than the hype around them.
The Overlap
Both pages share mathematics as their foundation: computer science, data science, and analytics are each a more specific application of it. Quantum computing is the applied end of computer science that interests me most (its algorithms, optimization, and routing especially), and it leans on the mathematical physics behind the theory, which is why it sits on the Quantum & Computer Science page instead of here. The data engineering, analytics, and applied NLP and machine-learning work on this page, including the GDELT/infoSpread pipeline and the agentic-coding synthesis, is the more general application.
The standard here is the researcher’s: data, methods, and results judged on the evidence, independent of the personal commitments elsewhere on this site. My political views are disclosed on their own page and are not premises in this work, and my spiritual life stays personal and makes no claims here. The names below mark intellectual debts, not endorsements of the people behind them.
Influences
Statisticians, engineers, and mathematicians who shaped how I work with data. Several of these ideas started with someone whose name didn't stick to them, so the earlier source is named beside the one history kept:
- - Claude Shannon: built the 1948 mathematical theory of communication (channel capacity, entropy as a measure of information) on top of Harry Nyquist's and Ralph Hartley's 1928 papers on signal-transmission rate and bandwidth, which Shannon himself cited as its foundation. The entropy formula's iconic S = k log W form is usually pinned on Boltzmann, but Boltzmann never wrote it that way; it's Max Planck's formalization, around 1900, of Boltzmann's 1870s statistical-mechanics work, the version now carved on Boltzmann's gravestone
- - John Tukey: co-published the 1965 Cooley-Tukey algorithm that made the Fast Fourier Transform practical on a computer, the same algorithm Carl Friedrich Gauss had worked out in 1805 to interpolate asteroid orbits, unpublished until 1866 and unrecognized as equivalent until years after Cooley and Tukey's paper. The box-and-whisker plot he introduced also had a precursor: Mary Eleanor Spear's range-bar charts, published in Charting Statistics in 1952
- - Edgar Codd: laid out the relational model in a single 1970 paper, A Relational Model of Data for Large Shared Data Banks, the theoretical basis for every SQL database since. IBM Research work, credited to him from the start; no erased co-author on this one
- - Judea Pearl: gave causal inference its modern graphical language, capped by the do-calculus (1995) and its completeness proof (2006), a formal test for when an observational question about cause and effect has an answer. He built on older ground: Sewall Wright's 1921 path analysis, which Pearl himself credits as causal inference's direct ancestor
- - Ada Lovelace: wrote out, in her 1843 notes on Babbage's Analytical Engine, an algorithm to compute Bernoulli numbers, usually called the first published computer program, for a machine that was never built. Historians disagree about how much of it was hers versus Babbage's; the narrower claim that holds up under that scrutiny is that she was the one who saw the machine could work on more than numbers
- - Alan Turing: the 1936 computability result is the theoretical floor under everything algorithmic on this page: it marks the line between what any machine can compute and what none ever will. His fuller story lives on the Quantum & Computer Science page
Past Affiliations
Iowa State
Senior design team, Aug 2024 – May 2025. Explainable AI for Source Code Applications
Mentors & References
Dr. Ali Jannesari (ISU Computer Science; explainable AI / ML) was the client and an advisor on this project, and I contributed to other research of his; Arushi Sharma was the project's advisor of record. Separately, Dr. Simanta Mitra (ISU CS teaching professor) mentored me through course and apprenticeship projects building applications for real clients.