new Progress article in Tourism Management, on forecasting in two-sided travel marketplaces. a demand model with supply left outside it is fitting a constraint it can't represent. the paper makes the case for treating both sides as one system. www.sciencedirect.com/science/arti...

Coupled supply and demand forecasting in platform accommodation markets

Tourism demand forecasting is methodologically mature, but it usually treats accommodation supply as fixed, exogenous, or slow-moving. This Progress i…

sciencedirect.com

New IJF paper. Booking lead times shift after launches and policy changes, and most models just average over the break, which leaves you biased for months. This one notices the shift and adapts. www.sciencedirect.com/science/arti...

Directional-shift Dirichlet ARMA models for compositional time series with structural break intervention

Compositional time series, vectors of proportions summing to unity, frequently exhibit structural breaks from external shocks or policy changes. We de…

sciencedirect.com

Listened back to my podcast episode, do not recommend as a hobby.I say "you know" a lot,"kind of" more, and there's a stretch where I hedge 3 times before finishing a thought.But the idea survives the filler: forecasting often isn't about accuracy. forecastingimpact.buzzsprout.com/1641538/epis...

Forecasting models trained on the past don't fail gracefully when the future breaks pattern. They hand you confident, well-calibrated, wrong answers. Our fix: let the markets a shock hits first inform the ones it hasn't reached yet. New on the Airbnb tech blog. medium.com/airbnb-engin...

When history fails you, borrow from geography

How Airbnb used sequential geographic recovery signals and prior propagation to generate reliable corridor-level forecasts when local data…

medium.com

What COVID did to our forecasting models (and what we built to handle the next shock) medium.com/airbnb-engin...

What COVID did to our forecasting models (and what we built to handle the next shock)

How Airbnb built forecasting models resilient enough to survive a global pandemic and whatever shock comes next.

medium.com

New paper out in the International Journal of Forecasting! B-DARCH is a Bayesian compositional volatility model for FX forecasting, developed at Airbnb with Rob Weiss (UCLA). A small glimpse into how we think about forecasting there. www.sciencedirect.com/science/arti...

A Bayesian Dirichlet autoregressive conditional heteroskedasticity model for forecasting currency shares

In marketplace finance, the daily mix of billing currencies is compositional data that drive forecasting, reporting, and treasury risk. We study Airbn…

sciencedirect.com

New preprint: Bayesian Dirichlet ARMA with directional-shift intervention for structural breaks in compositional time series. Applied to #Airbnb fee recognition during COVID. arxiv.org/abs/2601.16821

Directional-Shift Dirichlet ARMA Models for Compositional Time Series with Structural Break Intervention

Compositional time series, vectors of proportions summing to unity observed over time, frequently exhibit structural breaks due to external shocks, policy changes, or market disruptions. Standard meth...

arxiv.org

I spend a lot of my time at work thinking about lead times and one of the more interesting patterns is how differently bookings, trip length, & price behave as you move from far-out reservations to last-minute stays. New paper is really just structured curiosity about this: arxiv.org/abs/2601.12175

Distributional Fitting and Tail Analysis of Lead-Time Compositions: Nights vs. Revenue on Airbnb

We analyze daily lead-time distributions for two Airbnb demand metrics, Nights Booked (volume) and Gross Booking Value (revenue), treating each day's allocation across 0-365 days as a compositional ve...

arxiv.org

Staff DS role open on my team at Airbnb. Revenue forecasting systems: model selection, pipelines, automation. Work that actually gets used and scrutinized. Good mix of research and applications! #airbnb careers.airbnb.com/positions/75...

Staff Data Scientist, Forecasting-Finance - Careers at Airbnb

Airbnb was born in 2007 when two hosts welcomed three guests to their San Francisco …

careers.airbnb.com

Is Claude Code useful? Yes. Did it remove code instead of testing it when I prompted to write tests to increase coverage? Also yes