Posts

Working analyses in Python and R — trade statistics, forecasting, anomaly detection, and applied NLP — most of them built by directing an AI research assistant and reviewing its work. More about the approach here.

A Local RAG Chain for Donor Questions

Decompose, filter, rank, generate — running entirely on one machine, with no model API
rag
retrieval
embeddings
llm
python
Built by directing an AI research assistant: I set the goal, the success criteria, and the review at each step; Claude wrote and ran the code. Charity text comes from the Wik…
Sep 1, 2026
Aaron Koenigsberg

What Actually Works in a Consumer Complaint

88,673 credit-reporting complaints say specificity gets results and legal threats don’t. The formal letter format is the worst thing you can do.
consumer-finance
nlp
text-analysis
logistic-regression
r

Naming the accounts you’re disputing raises the relief rate from 56.6% to 70.4%. Threatening to sue lowers it. Writing ‘To Whom It May Concern’ lowers it more.

Aug 30, 2026
Aaron Koenigsberg

Hunting the Friendship Theme: Three Methods, One Album

music
nlp
python
embeddings

The LLM labelers found friendship in only 2 of 107 Carly Rae Jepsen songs. A fan knew better — and topic models, embedding probes, and a keyword audit back the fan.

Jul 13, 2026

Predicting Trade: The Upgrade That Wasn’t (Part 2)

Seasonal decomposition was supposed to fix the moving average. It didn’t — and the reason is that the problem wasn’t what we thought.
trade
forecasting
time-series
evaluation
python
Part of an ongoing series on IMF International Merchandise Trade Statistics (IMTS) data, built by directing an AI research assistant: I set the questions, the evaluation…
Jul 10, 2026
Aaron Koenigsberg

Carly Rae Jepsen’s Lyrical Themes, Mapped

music
nlp
python
claude-api

Two Claude models independently tag 183 CRJ songs against a 13-theme controlled vocabulary; the charts use only what they agree on.

May 3, 2026

Predicting Trade: Anomaly Detection via One-Step-Ahead Forecasting (Part 1)

Starting with the simplest possible baseline: a 12-month moving average
trade
forecasting
anomaly-detection
time-series
python
This post is part of an ongoing series on IMF International Merchandise Trade Statistics (IMTS) data, built entirely through vibe coding in Claude Dispatch. I describe the…
Apr 25, 2026
Aaron Koenigsberg

Trade as a Signal: Detecting Conflict-Driven Anomalies in IMF Merchandise Trade Data

trade
conflict
anomaly-detection
imf-imts
acled
python

Using rolling-average deviation and permutation testing to find where political violence and trade disruption coincide — and asking whether that overlap is more than chance.

Apr 17, 2026
No matching items