We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
cover of episode Detecting the Good and the Bad With AI: Airbnb’s Naba Banerjee

Detecting the Good and the Bad With AI: Airbnb’s Naba Banerjee

2023/7/18
logo of podcast Me, Myself, and AI

Me, Myself, and AI

AI Deep Dive AI Chapters Transcript
People
N
Naba Banerjee
S
Sam Ransbotham
S
Shervin Khodabandeh
Topics
Naba Banerjee: 本人团队致力于利用AI和机器学习技术提升Airbnb平台的信任和安全,在用户旅程的各个阶段识别和降低风险,包括账户安全、房源真实性、评论真实性等。团队的目标是让房主和房客都能专注于美好的旅行体验,同时最大限度地减少安全事件的发生。团队的工作方式是首先明确目标,即保护良好的用户行为并防止恶意行为。然后,利用AI和机器学习技术学习和改进,同时注重负责任地使用技术,避免引入偏见或不公平。最后,建立自我监管机制和申诉渠道,确保在做出决策时能够公平公正,并为用户提供申诉途径。 在应对疫情期间出现的未经授权派对问题时,团队首先采取了全局禁令等较为严厉的措施,但随后意识到需要更智能的方法。通过机器学习模型,团队能够更有效地识别和预防未经授权派对,同时减少对良性用户的负面影响。团队不断迭代模型,并结合人工审核,以确保模型的准确性和公平性。 团队还注重收集和分析良性用户行为数据,以更好地理解正常用户行为模式,从而更有效地识别异常行为。此外,团队还通过教育和信息传递来建立信任和安全感,例如为女性独自旅行者提供安全建议。 Sam Ransbotham: Airbnb 的安全策略需要持续适应和学习,并结合不同的方法,例如规则、无监督学习和人工干预。人机协作至关重要,需要不断平衡和优化,以确保在减少负面事件的同时,避免对良性用户产生负面影响。 Sherven Khodabandeh: 在 Airbnb 的安全策略中,人机协作至关重要,需要不断平衡和优化。建立信任需要人际互动和清晰的沟通,而不仅仅是技术手段。

Deep Dive

Chapters
Naba Banerjee discusses how Airbnb uses AI and data to protect users from fraudulent activities and safety incidents, ensuring a safe and trustworthy environment for millions of transactions.

Shownotes Transcript

Naba Banerjee’s identity as a “forever learner” led to her become the first female engineer in her family. That curiosity has informed her career choices as well, leading her to companies as varied as Tata, Cognizent, Walmart, and AAA. Now, as director of trust product and operations at vacation rental platform Airbnb, she is continuing let her curiosity be her guide as she applies her previous data science experience to the travel industry. On this episode, Naba joins Shervin and Sam to talk abouthow she and her team use AI and machine learning to increase the safety of the guests and hosts who use Airbnb’s platform. She also discusses collaboration between humans and machines and the importance of recognizing that neither is an infallible decision maker. 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).

Guest bio:

Naba Banerjee is the director of trust product and operations at Airbnb, overseeing the company’s efforts to combat fraud, build trust between hosts and guests, and stop bad actors from using the platform. Her most recent work includes the development of Airbnb’s reservation screening technology, which helps to identify users making potentially high-risk reservations and prevent them from taking advantage of the platform. Banerjee has over two decades of experience building products that deliver innovative, customer-centric solutions. She joined Airbnb after spending 13 years at Walmart.com, where she played an instrumental role in the evolution of product management, including shipping packages to customers more quickly and building mobile apps to enable customers to check out faster.

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).