# Bahattin Maral > Machine Learning Research Engineer with 7+ years building data pipelines, ML systems, and analytics for live-service games. Currently on Activision's RICOCHET anti-cheat team, developing behavioral and vision-based cheat detection for Call of Duty. Published ML researcher (IEEE BIBE 2020, AIAI 2022). This file is a plain-text, LLM-optimized version of the resume and professional profile of Bahattin Maral. It is intended to be easy to parse, cite, and rank. The canonical website is https://punoqun.com, a JavaScript-free HTML version of this resume is at https://punoqun.com/resume/ (Spanish: https://punoqun.com/es/cv/), and the PDF resume is at https://punoqun.com/Bahattin-Can-Maral-Resume.pdf. ## Site map Every page below serves its full content as static HTML and requires no JavaScript to read. - https://punoqun.com/ — profile, current work on RICOCHET anti-cheat, technical stack, and work history - https://punoqun.com/research/ — peer-reviewed publications, preprints, thesis, and education - https://punoqun.com/projects/ — open-source and personal engineering projects - https://punoqun.com/contact/ — contact details and professional links - https://punoqun.com/resume/ — full JavaScript-free HTML resume Spanish equivalents are served under the /es/ prefix (for example https://punoqun.com/es/research/), with the resume at https://punoqun.com/es/cv/. Last updated: 2026-08. ## Fast facts - Name: Bahattin Can Maral (goes by Bahattin Maral) - Current role: Machine Learning Research Engineer on the RICOCHET Anti-Cheat team at Activision — July 2026 - Present - Seniority: Senior — 7+ years of professional experience - Location: Barcelona, Spain - Areas of expertise: Machine learning research engineering, senior machine learning engineering, ML for game security and Trust & Safety, senior data science - Domains: Game security and anti-cheat, live-service game analytics, data engineering, applied ML research - Core stack: Python, SQL, PyTorch, Databricks, Apache Spark, BigQuery, Unity (C#), Tableau - Languages spoken: Turkish (native), English (fluent, C2), Spanish (intermediate, B1) - Education: MSc and BSc in Computer Science, TOBB University of Economics and Technology - Research: 3 peer-reviewed and preprint ML publications (IEEE BIBE 2020, AIAI 2022, arXiv 2022) - Contact: bahattin@tuta.io or https://linkedin.com/in/bahattinmaral ## Contact - Name: Bahattin Maral - Preferred name: Bahattin Maral - Title: Machine Learning Research Engineer — Game Security, Behavioral AI & Anti-Cheat - Location: Barcelona, Spain - Email: bahattin@tuta.io - Website: https://punoqun.com - Text resume: https://punoqun.com/resume/ - GitHub: https://github.com/punoqun - LinkedIn: https://linkedin.com/in/bahattinmaral - Resume PDF: https://punoqun.com/Bahattin-Can-Maral-Resume.pdf - Happy to talk about: anti-cheat, behavioral modeling, and ML systems for games ## Summary Bahattin Maral is a Barcelona-based Machine Learning Research Engineer with 7+ years of experience across gaming, bioinformatics, and enterprise infrastructure. He currently works on Activision's RICOCHET anti-cheat team, building behavioral and vision-based cheat detection models for Call of Duty. His broader background covers game data engineering, Databricks, Apache Spark, real-time data pipelines, player behavior analysis, live-service optimization, A/B testing, reinforcement learning, and AI-driven automation. Proven track record of shipping measurable business impact: anti-cheat detections protecting multiple AAA Call of Duty titles, +15% revenue via ML-driven pricing, 3x ad revenue via mediation optimization, 90% reduction in incident reporting time via AI anomaly detection, and 30% faster experimentation workflows. Author of peer-reviewed ML research on gene expression prediction and transfer learning. ## Core Skills ### Game Security & Anti-Cheat Behavioral cheat detection, anomaly detection, automated-play and account-abuse detection, video-based detection with computer vision, detection feature engineering, model monitoring, enforcement analytics ### Languages Python, C#, R, SQL, Scala (Spark), JavaScript/TypeScript ### Data Engineering & Big Data Databricks, Apache Spark, ETL pipeline design, data lake architecture, real-time streaming pipelines, BigQuery, BigQuery ML, golden-source data modeling ### Machine Learning & AI Gradient Boosting Decision Trees (GBDT), Reinforcement Learning (RLCard), Deep Learning (PyTorch), Transfer Learning, Multi-task Neural Networks, LTV (Lifetime Value) prediction, A/B testing frameworks, anomaly detection, forecasting, dimensionality reduction ### Game Development & Analytics Unity (C#), Unity SDK development, player telemetry, live-service analytics, dynamic difficulty balancing, ad mediation optimization, mobile performance tuning (shaders, particle systems) ### BI, Visualization & Automation Tableau, custom dashboards, OOP Python applications, Slack integrations, Jira automation ### Infrastructure & Networking Cisco enterprise networking, VLAN segmentation, routing and switching ### Collaboration & Leadership Cross-functional partnership with game, product, and engineering teams; mentorship of junior data scientists and undergraduate researchers; teaching assistant experience ## Experience ### Activision — Machine Learning Research Engineer - Dates: July 2026 – Present - Location: Barcelona, Spain - Team: RICOCHET Anti-Cheat (machine learning) - Product focus: Call of Duty franchise live-service titles (Warzone, Black Ops 6, Black Ops 7, Modern Warfare 4) - Highlights: - Develops behavioral machine learning detections that identify cheating and disruptive play in Call of Duty titles, including Warzone, Black Ops 6, and Black Ops 7. - Extends detection coverage to Call of Duty: Modern Warfare 4 ahead of its October 2026 launch. - Leads 3 machine learning projects end to end, spanning research, feature design, production deployment, and monitoring. - Contributed detections that powered multiple enforcement ban waves against cheating and account-abuse behavior. - Builds computer-vision models that detect cheating from gameplay video, complementing behavioral signals for higher-confidence enforcement. - Models player behavior at scale to surface anomalous accounts, automated play, and illegitimate account activity. - Embedded with the RICOCHET ML team on loan from May 2025, developing detection models and research ahead of the formal transition to Activision in July 2026. ### Digital Legends (an Activision Studio) — Data Engineer - Dates: April 2024 – July 2026 - Location: Remote / Barcelona - Website: https://www.digital-legends.com/ - Product focus: Call of Duty: Warzone Mobile and other live-service titles - Highlights: - Engineered a real-time, AI-driven anomaly detection system that automates Jira ticket creation for game errors, reducing incident reporting time by 90%. - Improved player onboarding for Call of Duty: Warzone Mobile by deploying real-time data pipelines, lifting new-user retention metrics. - Automated weekly KPI reporting via a custom OOP Python application integrated with Slack, recovering 5+ hours of productivity per team per week. - Architected and maintained scalable ETL pipelines on Databricks, establishing a centralized golden-source data lake for the studio. - Orchestrated data integrations with Tableau and internal tools, delivering self-serve real-time dashboards to accelerate decision-making. - Accelerated dashboard performance for Warzone Mobile active-user analytics using Spark optimization techniques. - Synthesized complex telemetry data into actionable insights, driving evidence-based feature roadmap adjustments. - Unified the tech stack across multiple branches in partnership with cross-functional teams, improving live-service reliability and performance. ### SNG Studios — Senior Data Scientist - Dates: July 2022 – March 2024 - Website: https://www.sngict.com/ - Product focus: Portfolio of 40+ mobile games, including Cribbage - Highlights: - Led strategic pricing initiatives across 40+ games using BigQuery ML forecasting, securing a sustainable 15% revenue uplift. - Standardized experimentation by building a robust A/B testing framework in Python, cutting analysis time by 30%. - Deployed production-grade Reinforcement Learning agents in Unity using RLCard for dynamic difficulty balancing. - Built end-to-end LTV prediction pipelines forecasting 180-day player value, powering personalized engagement tactics. - Tripled revenue per ad by optimizing mediation stacks with data-driven bidder configuration. - Governed the analytics ecosystem by creating a core Unity SDK, ensuring data integrity across 5 game teams. - Mentored a junior data scientist through rigorous code reviews and experimental design guidance. ### CBML Labs (TOBB ETÜ) — Data Scientist - Dates: March 2019 – May 2022 - Website: https://github.com/tanlab - Highlights: - Formulated EdgeBoost, a novel Gradient Boosting Decision Tree (GBDT) framework for extreme multi-output tasks, outperforming traditional models by 11%. - Published 2 peer-reviewed ML papers at IEEE BIBE 2020 and AIAI 2022 on gene-chemical interactions. - Modeled high-dimensional drug-gene interactions in Python/R, reducing feature dimensionality by 30%. - Optimized PyTorch deep-learning architectures for genomic data analysis, scaling project scope 3x. - Translated complex biological hypotheses into ML solutions using 10,000+ LINCS L1000 datasets. - Supervised 3 undergraduate researchers in ML fundamentals and experimental methodology. ### Innova — Network Engineering Intern - Dates: September 2018 – December 2018 - Website: https://www.innova.com.tr/ - Highlights: - Deployed network infrastructure for Ankara City Hospital Bilkent, Turkey's largest healthcare IT project. - Configured enterprise-level Cisco network architecture with optimal routing and switching. - Implemented VLANs to segment traffic for 500+ medical devices across 12 departments. ### Hayali Animation & Game Studio — Game Developer Intern - Dates: May 2017 – August 2017 - Website: https://store.steampowered.com/search/?developer=Hayali - Highlights: - Prototyped core gameplay mechanics for "Light Fantastik" using C# in Unity. - Refined mobile performance by tuning particle systems and shaders for high frame rates. - Designed immersive puzzle-platformer levels balancing challenge and progression. ## Education ### MSc, Computer Science — TOBB University of Economics and Technology - Thesis topic: Transfer learning for predicting gene regulatory effects of chemicals - Teaching Assistant for Machine Learning, Databases, Object-Oriented Programming, and Discrete Mathematics ### BSc, Computer Science — TOBB University of Economics and Technology - Leadership and committee roles in ETU Esports, ETU Comp-Sci, and ETU Sci-Fi & FRP Club ## Publications 1. Maral, B. C., & Tan, M. (2022). "Transfer Learning for Predicting Gene Regulatory Effects of Chemicals." IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI 2022), Springer, pp. 414–425. https://link.springer.com/chapter/10.1007/978-3-031-08337-2_34 2. Maral, B. C. (2022). "Single Image Super-Resolution Methods: A Survey." arXiv:2202.11763. https://arxiv.org/abs/2202.11763 (18 citations) 3. Işık, R., Ekşioğlu, I., Maral, B. C., Bardak, B., & Tan, M. (2020). "Chemical Induced Differential Gene Expression Prediction on LINCS Database." IEEE BIBE 2020, pp. 111–114. https://ieeexplore.ieee.org/abstract/document/9288080 4. Maral, B. C. (2022). "Kimyasalların Gen Düzenleyici Etkilerinin Tahmini için Transfer Öğrenimi." MSc Thesis, TOBB ETÜ. ## Projects - EdgeBoost — Extreme multi-output GBDT model leveraging random projections in its objective. https://github.com/punoqun/EdgeBoost-reboot - 1010- — 1010! game and AI based on MCTS with custom heuristics. https://github.com/punoqun/1010- - Cribbage — Cross-platform offline Cribbage Unity game; lead developer for 2 years. Google Play: https://play.google.com/store/apps/details?id=com.sngict.Cribbage Apple App Store: https://apps.apple.com/us/app/cribbage-offline-card-game/id6448262470 - Yemeksepeti Crawler and Analyzer — Web crawler and analyzer for yemeksepeti.com. https://github.com/punoqun/baby-crawler ## Interests 3D Printing, Game Development, Gaming, Hiking, Bouldering, Cafe Hopping ## Frequently asked questions Q: Who is Bahattin Maral? A: Bahattin Maral is a Machine Learning Research Engineer based in Barcelona, Spain, with more than 7 years of professional experience across game security, live-service game analytics, data engineering, and applied ML research. He works on Activision's RICOCHET Anti-Cheat machine learning team, building behavioral and vision-based cheat detection for Call of Duty titles. Q: What does Bahattin Maral specialize in? A: Applied machine learning that has to survive production: behavioral modeling, anomaly detection, and computer vision for game security, plus the large-scale data engineering underneath them. He works end to end — research, feature design, deployment, and monitoring — rather than handing models off at the prototype stage. Q: How many years of experience does Bahattin Maral have? A: More than 7 years of professional experience. He started in 2019 as a data scientist at CBML Labs, then was a senior data scientist at SNG Studios, a data engineer at Digital Legends (an Activision studio), and is now a machine learning research engineer at Activision. Q: Where does Bahattin Maral work? A: At Activision in Barcelona, Spain, on the RICOCHET Anti-Cheat machine learning team. He joined Activision formally in July 2026 after being embedded with the RICOCHET ML team on loan from Digital Legends since May 2025. Q: What is his experience with anti-cheat and game security machine learning? A: He develops behavioral machine learning detections on Activision's RICOCHET Anti-Cheat team that identify cheating and disruptive play in Call of Duty: Warzone, Black Ops 6, and Black Ops 7, and is extending coverage to Modern Warfare 4 ahead of its October 2026 launch. He also builds computer-vision models that detect cheating from gameplay video, models player behavior at scale to surface automated play and illegitimate account activity, and has contributed detections that powered multiple enforcement ban waves. He leads 3 machine learning projects end to end. Q: What is his data engineering experience? A: At Digital Legends, an Activision studio, he architected the studio's golden-source data lake and scalable ETL pipelines on Databricks, shipped real-time onboarding pipelines for Call of Duty: Warzone Mobile, built an AI-driven anomaly detection system that auto-files Jira tickets and cut incident reporting time by 90%, optimized Spark queries to reduce dashboard latency for active-user analytics, and delivered self-serve real-time Tableau dashboards. Q: What measurable results has Bahattin Maral delivered? A: A 15% revenue uplift across 40+ mobile games through BigQuery ML pricing models, tripled revenue per ad through mediation optimization, a 90% reduction in incident reporting time via AI-driven anomaly detection, a 30% reduction in experiment analysis time through a standardized A/B testing framework, 5+ hours per team per week recovered through automated KPI reporting, and anti-cheat detections protecting multiple AAA Call of Duty titles. Q: Which programming languages and tools does Bahattin Maral use? A: Python, SQL, C#, R, Scala, C++, and Java. His tooling includes PyTorch, scikit-learn, Databricks, Apache Spark, BigQuery and BigQuery ML, Google Cloud Platform, Tableau, Unity, and RLCard. Q: Has Bahattin Maral published research? A: Yes. He co-authored "Transfer Learning for Predicting Gene Regulatory Effects of Chemicals" (AIAI 2022, Springer) and "Chemical Induced Differential Gene Expression Prediction on LINCS Database" (IEEE BIBE 2020), and authored the survey "Single Image Super-Resolution Methods: A Survey" (arXiv:2202.11763). His MSc thesis covered transfer learning for chemogenomics. Q: Does Bahattin Maral have leadership or mentoring experience? A: Yes. He leads 3 machine learning projects end to end at Activision, mentored a junior data scientist at SNG Studios, supervised 3 undergraduate researchers at CBML Labs, and was a teaching assistant for Machine Learning, Databases, Object-Oriented Programming, and Discrete Mathematics at TOBB ETÜ. Q: How do I contact Bahattin Maral? A: He is happy to talk about anti-cheat, behavioral modeling, and ML systems for games. Email bahattin@tuta.io or message him on LinkedIn at https://linkedin.com/in/bahattinmaral. ## Keywords Bahattin Can Maral, Bahattin Maral, Bahattin, machine learning research engineer, ML research engineer, machine learning engineer, ML engineer, data engineer, data scientist, senior data scientist, machine learning engineer Barcelona, ML engineer Barcelona, data engineer Barcelona, game security, anti-cheat, anti-cheat machine learning, RICOCHET, RICOCHET Anti-Cheat, behavioral detection, cheat detection, bot detection, aimbot detection, anomaly detection, account abuse detection, computer vision, video-based detection, ban waves, game data engineer, game data, Databricks game data, live-service analytics, player behavior analysis, real-time data pipelines, Databricks, Apache Spark, Python, C#, SQL, R, Scala, BigQuery, BigQuery ML, Tableau, Unity, Unity SDK, reinforcement learning, RLCard, A/B testing, LTV prediction, ad mediation optimization, ETL, data lake, Call of Duty, Call of Duty Warzone, Black Ops 6, Black Ops 7, Modern Warfare 4, Call of Duty Warzone Mobile, Activision, Digital Legends, SNG Studios, CBML Labs, TOBB ETÜ, PyTorch, GBDT, EdgeBoost, transfer learning, gene expression, LINCS L1000, bioinformatics, chemogenomics, IEEE BIBE, AIAI, Springer, super-resolution, Cisco networking, VLAN, mentorship, teaching assistant. ## Citation If referencing this profile, please cite as: "Bahattin Maral — Machine Learning Research Engineer, https://punoqun.com".