We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
cover of episode Trust and Fraud Detection at Scale: Instagram’s Stephanie Moyerman

Trust and Fraud Detection at Scale: Instagram’s Stephanie Moyerman

2023/5/9
logo of podcast Me, Myself, and AI

Me, Myself, and AI
AI Deep Dive AI Chapters Transcript
People
S
Sam Ransbotham
S
Stephanie Moyerman
Topics
Stephanie Moyerman: 本人担任Instagram用户福祉数据科学总监，致力于利用人工智能和数据提升平台的信任度、安全性和完整性。数据显示，尽管社交媒体存在负面问题，但青少年在过去几十年里的整体安全和福祉有所提高。通过大规模个性化模型，Instagram可以促进健康社会规范，鼓励积极互动，并提高对积极内容的认识。大规模人工智能模型帮助Instagram检测和调节有害内容，保护用户免受不良信息的影响。检测欺诈和滥用行为是一个对抗性博弈，需要不断改进技术和策略才能跟上不断变化的挑战。尽管存在恶意行为者，但大多数人本质上是善良的，理解行为背后的动机对于构建更安全的平台至关重要。为了有效评估和改进人工智能模型，需要一个封闭的反馈循环，以便根据现实世界的反馈不断迭代。缺乏封闭的反馈循环会导致人工智能模型仅从自身学习，最终可能出现问题。用户反馈对于改进人工智能算法至关重要，平台需要方便用户提供反馈并支持其操作。她最担心的是数据科学领域缺乏经验丰富的从业者。她希望人工智能能够应用于解决全球性问题，例如粮食短缺和疾病。 Sam Ransbotham: 讨论了人工智能在检测不当行为和内容方面的作用，以及在算法决策中平衡自由表达和安全性的挑战。强调了在人工智能算法中建立公平性和伦理考量的必要性，以及对具有哲学素养的专业人员的需求。 Shervin Khodabandeh: 与Stephanie Moyerman一起探讨了人工智能在检测欺诈和滥用行为中的作用，以及如何利用数据来改善社交媒体平台的用户体验。关注了人工智能算法的公平性和伦理问题，以及在快速发展的数字领域中保持安全和公平的管理挑战。

Deep Dive

Chapters
Stephanie Moyerman discusses how AI and data science are used to improve trust, safety, and integrity on platforms like Instagram, highlighting the role of AI in detecting harmful content and fostering positive social norms.

Shownotes Transcript

Stephanie Moyerman’s background in cosmology and astrophysics — where she worked with large data sets, looking for a signal among what was mostly noise — prepared her well for a career in data science and ethics. Today, she is the data science director of well-being at Instagram, where she works to enhance trust, safety, and integrity for users of the social media platform.

Stephanie joins Sam and Shervin on this episode to discuss how applying artificial intelligence to social media enables Instagram to detect fraud and abuse at scale to help protect users, as well as the importance of human input in AI feedback loops and the need for more experienced practitioners in the field. Read the episode transcript here).

*Me, Myself, and AI *is a collaborative podcast from MIT Sloan Management Review and Boston Consulting Group and is hosted by Sam Ransbotham and Shervin Khodabandeh. Our engineer is David Lishansky, and the coordinating producers are Allison Ryder and Sophie Rüdinger.

Stay in touch with us by joining our LinkedIn group, AI for Leaders at mitsmr.com/AIforLeaders) or by following Me, Myself, and AI on LinkedIn).

*NEW! For specific takeaways from this episode and guidance on how you can implement them in your own work, download our episode toolkit here).

Guest bio:

Stephanie Moyerman is the data science director of well-being at Instagram, where she works to minimize negative experiences and maximize positive experiences on the platform. Previously, she was the senior director of risk and trust science at eBay and a senior science manager in Amazon’s Customer Trust and Partner Support unit, where she worked to protect the e-commerce platforms from bad actors.

Moyerman has a doctorate in physics (experimental cosmology) and a master’s in computational science, math, and engineering from the University of California, San Diego. She also has dual bachelor’s degrees in mathematics and physics from Harvey Mudd College.

Moyerman enjoys many hobbies, including running, hiking, surfing, snowboarding, judo, jujitsu, glassblowing, flying airplanes, and racing cars.

We encourage you to rate and review our show. Your comments may be used in Me, Myself, and AI materials.

We want to know how you feel about Me, Myself, and AI. Please take a short, two-question survey).