<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Research on Aditya Kurniawan (Akur)</title><link>https://akurniawan.github.io/categories/research/</link><description>Recent content in Research on Aditya Kurniawan (Akur)</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 27 Aug 2025 00:00:00 +0700</lastBuildDate><atom:link href="https://akurniawan.github.io/categories/research/index.xml" rel="self" type="application/rss+xml"/><item><title>Bitcoin Regime Analysis, Part 2: What Each Feature Buys You</title><link>https://akurniawan.github.io/posts/btc_regime_modeling/</link><pubDate>Wed, 27 Aug 2025 00:00:00 +0700</pubDate><guid>https://akurniawan.github.io/posts/btc_regime_modeling/</guid><description>Volatility buys long regimes with no direction. Volume buys direction but halves regime length. Fractional differencing buys length back and destroys direction completely. Every one of those is a trade, not an improvement.</description></item><item><title>Bitcoin Regime Analysis, Part 1: What the Data Looks Like Before You Model It</title><link>https://akurniawan.github.io/posts/btc_regime_eda/</link><pubDate>Tue, 26 Aug 2025 00:00:00 +0700</pubDate><guid>https://akurniawan.github.io/posts/btc_regime_eda/</guid><description>Bitcoin&amp;rsquo;s returns are almost unpredictable in the mean, wildly structured in the variance, and nothing like a normal distribution. This is a walk through the checks that establish that, and why they point at Hidden Markov Models.</description></item><item><title>Indonesian Language Model</title><link>https://akurniawan.github.io/posts/indonesian-language-model/</link><pubDate>Tue, 11 Dec 2018 00:00:00 +0700</pubDate><guid>https://akurniawan.github.io/posts/indonesian-language-model/</guid><description>A deep dive into building state-of-the-art Indonesian language models using AWD-LSTM architecture. This post covers the challenges of working with low-resource languages, implementation details, and experimental results from production systems at Traveloka.</description></item></channel></rss>