<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Alex Oswald — Writing</title><description>Essays and worked analysis on game analytics, experimentation, and economics.</description><link>https://alexoswald.ca/</link><language>en-us</language><item><title>The Election-Year Install Tax</title><link>https://alexoswald.ca/writing/election-year-cpi/</link><guid isPermaLink="true">https://alexoswald.ca/writing/election-year-cpi/</guid><description>US install prices rise in the fourth quarter of an election year because presidential campaigns are bidding for the same impressions. It is real, it is specific to one market, and it is the one piece of seasonality you cannot fit.</description><pubDate>Tue, 25 Aug 2026 00:00:00 GMT</pubDate><category>Elections</category><category>us elections</category><category>user acquisition</category><category>cpi</category><category>political advertising</category><category>game analytics</category><category>forecasting</category></item><item><title>Cohort LTV Forecasting</title><link>https://alexoswald.ca/writing/series/cohort-ltv-forecasting/</link><guid isPermaLink="true">https://alexoswald.ca/writing/series/cohort-ltv-forecasting/</guid><description>Spend to CPI to installs to actives to spenders to revenue per user to LTV. Seven links, each with its own estimator, and a chain whose weakest point is not where anyone expects it.</description><pubDate>Mon, 24 Aug 2026 00:00:00 GMT</pubDate><category>Game analytics</category><category>forecasting</category><category>cohort analysis</category><category>ltv</category><category>user acquisition</category></item><item><title>A/B Testing in Games</title><link>https://alexoswald.ca/writing/series/ab-testing-in-games/</link><guid isPermaLink="true">https://alexoswald.ca/writing/series/ab-testing-in-games/</guid><description>A decade of running experiments on live games, reduced to seventeen rules anyone can apply, a worked case study for each way an experiment lies to you, and the module I built so the pipeline refuses to make the same mistakes twice.</description><pubDate>Sun, 23 Aug 2026 00:00:00 GMT</pubDate><category>Game analytics</category><category>a/b testing</category><category>experimentation</category><category>causal inference</category><category>live service</category></item><item><title>Why Simulate Demand</title><link>https://alexoswald.ca/writing/series/why-simulate-demand/</link><guid isPermaLink="true">https://alexoswald.ca/writing/series/why-simulate-demand/</guid><description>Bias requires truth. A simulator lets you set the truth, hand an estimator only the observable view, and measure how far off it lands — the one measurement real market data can never give you.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate><category>Economics</category><category>demand estimation</category><category>causal inference</category><category>simulation</category></item><item><title>Savepoint Analytics</title><link>https://alexoswald.ca/writing/savepoint-analytics/</link><guid isPermaLink="true">https://alexoswald.ca/writing/savepoint-analytics/</guid><description>I believe in the 80/20 rule — right up until the last 20% is the answer. What Savepoint is, why it exists, and the one idea it is organized around.</description><pubDate>Wed, 15 Apr 2026 00:00:00 GMT</pubDate><category>Game analytics</category></item></channel></rss>