https://ktavabi.github.io/Recent content on Kambiz TavabiHugoenMon, 01 Sep 2025 00:00:00 +0000https://ktavabi.github.io/projects/ooc-analytics/Mon, 01 Sep 2025 00:00:00 +0000https://ktavabi.github.io/projects/ooc-analytics/<p>Six-year operational intelligence study on inter-county violator flows, data quality, and cooperation across Washington counties.</p>https://ktavabi.github.io/projects/apcd-healthcare/Tue, 01 Jul 2025 00:00:00 +0000https://ktavabi.github.io/projects/apcd-healthcare/<p>Multi-year analysis linking statewide claims-style data to DOC release cohorts under strict access controls.</p>https://ktavabi.github.io/projects/imrs-nlp/Sun, 01 Sep 2024 00:00:00 +0000https://ktavabi.github.io/projects/imrs-nlp/<p>End-to-end NLP system replacing manual labeling of correctional incident free text with automated multi-label prediction across facilities.</p>https://ktavabi.github.io/photos/img_0034/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_0034/https://ktavabi.github.io/photos/img_0088/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_0088/https://ktavabi.github.io/photos/img_0123/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_0123/https://ktavabi.github.io/photos/img_0129/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_0129/https://ktavabi.github.io/photos/img_0195/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_0195/https://ktavabi.github.io/photos/img_8470/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_8470/https://ktavabi.github.io/photos/img_9252/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_9252/https://ktavabi.github.io/photos/img_9369/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_9369/https://ktavabi.github.io/photos/img_9453/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_9453/https://ktavabi.github.io/photos/img_9660/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_9660/https://ktavabi.github.io/photos/img_9684/Mon, 01 Jan 2024 00:00:00 +0000https://ktavabi.github.io/photos/img_9684/https://ktavabi.github.io/projects/experiment-design/Fri, 01 Sep 2023 00:00:00 +0000https://ktavabi.github.io/projects/experiment-design/<p>A/B and quasi-experimental frameworks applied to large administrative datasets for defensible program decisions.</p>https://ktavabi.github.io/projects/bios-enterprise-bi/Tue, 01 Aug 2023 00:00:00 +0000https://ktavabi.github.io/projects/bios-enterprise-bi/<p>Program-scale delivery of dashboards, recurring reports, and data pipelines for executive, legislative, and operational stakeholders.</p>https://ktavabi.github.io/projects/temporal-projection/Fri, 01 Jun 2018 00:00:00 +0000https://ktavabi.github.io/projects/temporal-projection/<p>Combined temporal projection noise suppression approaches to improve MEG signal quality for downstream modeling.</p>https://ktavabi.github.io/projects/mne-bids/Mon, 01 Jan 2018 00:00:00 +0000https://ktavabi.github.io/projects/mne-bids/<p>Python tooling to organize electrophysiological data in BIDS format and streamline analysis &ndash; reducing setup friction for labs worldwide.</p>https://ktavabi.github.io/projects/reading-circuitry/Mon, 01 Jun 2015 00:00:00 +0000https://ktavabi.github.io/projects/reading-circuitry/<p>Python ML pipelines for speech-related neural responses in school-aged children; neural networks, PCA, and dense-array time-series modeling.</p>https://ktavabi.github.io/projects/predictive-meg/Thu, 01 Jan 2015 00:00:00 +0000https://ktavabi.github.io/projects/predictive-meg/<p>Python pipelines from 306-channel MEG time series to predictive models of language and reading outcomes across pediatric cohorts.</p>https://ktavabi.github.io/projects/infant-language/Wed, 01 Jan 2014 00:00:00 +0000https://ktavabi.github.io/projects/infant-language/<p>ML and feature engineering linking infant neurophysiology to later language measures.</p>https://ktavabi.github.io/projects/cohort-engineering/Sat, 01 Jan 2011 00:00:00 +0000https://ktavabi.github.io/projects/cohort-engineering/<p>12-year pediatric program infrastructure: scalable Python and MATLAB pipelines, signal space separation, artifact rejection, multi-table integration.</p>https://ktavabi.github.io/projects/language-impairment/Fri, 01 Jan 2010 00:00:00 +0000https://ktavabi.github.io/projects/language-impairment/<p>Regulatory-style validation of a speech-discrimination biomarker for language impairment in autism using blinded ROC and mixed models.</p>https://ktavabi.github.io/projects/auditory-oddball/Thu, 01 Jan 2009 00:00:00 +0000https://ktavabi.github.io/projects/auditory-oddball/<p>Four-condition auditory oddball design across two cohorts (N = 96+) to resolve contradictory literature via larger samples (5-8x prior work).</p>https://ktavabi.github.io/projects/mrc-cambridge/Fri, 01 Jun 2007 00:00:00 +0000https://ktavabi.github.io/projects/mrc-cambridge/<p>Spoken word recognition, lexical/semantic processing with Prof. Friedemann Pulvermuller; plasticity paradigms.</p>https://ktavabi.github.io/projects/phd-phonological/Thu, 01 Jan 2004 00:00:00 +0000https://ktavabi.github.io/projects/phd-phonological/<p>Dissertation research on phonological processing using MEG; speech feature encoding (P50m/N100m); thesis advising.</p>https://ktavabi.github.io/projects/grad-deafness/Tue, 01 Jan 2002 00:00:00 +0000https://ktavabi.github.io/projects/grad-deafness/<p>Peripheral visual space representation in congenital deafness; cortical magnification paradigms; diffusion tensor imaging of geniculocortical pathway.</p>https://ktavabi.github.io/projects/feline-morphometry/Thu, 01 Jan 1998 00:00:00 +0000https://ktavabi.github.io/projects/feline-morphometry/<p>Histology-driven volumetric morphometry of neocortex, white matter, and substantia nigra across development.</p>https://ktavabi.github.io/about/Mon, 01 Jan 0001 00:00:00 +0000https://ktavabi.github.io/about/<h2 id="kambiz-tavabi">Kambiz Tavabi</h2> <p>Ph.D. applied scientist and engineering manager building production machine learning, statistical evaluation, and data platforms in complex, regulated environments.</p> <p>I lead Business Intelligence &amp; Operations Surveillance at the Washington State Department of Corrections (Research &amp; Data Analytics). Recent work includes a production multi-label NLP system over 110K+ records and 73 labels (scikit-learn / TF-IDF; 75.6% micro-F1, 88.3% precision; k-fold and Jaccard evaluation; human-in-the-loop iteration), SQL ETL (T-SQL, Oracle) feeding Power BI at scale, automation that cut reporting cycle time roughly 60-70%, and experiment design (A/B and quasi-experiments; chi-square, Cramer&rsquo;s V) on large administrative and privacy-constrained healthcare claims cohorts &ndash; including geospatial and network analytics (GeoPandas, NetworkX, Quarto) on large-scale data.</p>https://ktavabi.github.io/cv/Mon, 01 Jan 0001 00:00:00 +0000https://ktavabi.github.io/cv/<link rel="stylesheet" href="https://ktavabi.github.io/css/cv.css"> <div class="cv-header"> <h1>Kambiz Tavabi</h1> <div class="cv-contact"> Seattle, WA | <a href="mailto:ktavabi@gmail.com">ktavabi@gmail.com</a> | <a href="https://github.com/ktavabi">GitHub</a> | <a href="https://www.linkedin.com/in/kambiz-tavabi-hu93255326b/">LinkedIn</a> | </div> </div> <div class="cv-section"> <h2>Professional Summary</h2> <p>Senior Data Scientist and NIH-recognized researcher with 15+ years deploying ML solutions in high-stakes environments from healthcare to corrections. I help organizations make critical decisions faster through production NLP systems and privacy-compliant analytics, with expertise in translational clinical research that led to breakthrough electrophysiological biomarkers for autism spectrum disorders. At Washington DOC, I built ML pipelines that improved incident classification accuracy 30-fold while managing complex multi-table ETL across restricted datasets. My expertise spans end-to-end model development, A/B testing frameworks, and leading cross-functional teams to deliver executive-grade insights under strict regulatory constraints.</p>