SBIR Phase I: Using big data, AI, and machine learning in gender equality and social inclusion analysis

SBIR 第一阶段：利用大数据、人工智能和机器学习进行性别平等和社会包容分析

• 批准号: 1843248
• 负责人: Jessica Menon
• 金额: $ 22.48万
• 依托单位: EQUILO INC.
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-02-01 至 2019-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1843248&HistoricalAwards=false
• 关键词: SBIR; Phase; Using; big; data

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to enable economic development aid organizations to plan, implement, measure, and achieve better gender equality and social inclusion outcomes. Gender equality is recognized as an important factor in catalyzing development and lifting communities out of poverty. Empowered women contribute to healthy and productive families, communities, and nations. An important step in doing this is to integrate high quality and timely gender analysis (examination of how differences in gender roles, activities, needs, and opportunities affect men, women, girls and boys in specific contexts), into decision-making and project planning. For both public and private sectors, early, action-oriented gender analysis is vital to tackle improve outcomes. In 2015 - 2016, OECD aid agencies spent, on average, $41.7 billion per year targeting gender equality and women's empowerment. Conservatively estimating that 3-5% of this expenditure is for gender analysis and action planning, that makes a market of $1.3-2.1 billion in the development sector alone. This project can potentially improve outcomes from that development funding.This Small Business Innovation Research (SBIR) Phase I project is to develop and test a web-based application that automates the currently manual process of conducting gender analyses. This addresses a real world challenge faced by aid organizations to effectively integrate gender analyses into planning to inform effective and timely decision-making. Despite being a requirement by many organizations, there are procurement and contract delays, shortage of gender experts, and manual research and data collection. This project will develop a machine learning model that leverages big data, APIs, and text-mining, driven by an analytic framework created by experts, to automate this process and deliver customized results instantly for a fraction of the cost. Phase I will build, train, and test the model for one sector and select countries. By the end of Phase I, the model will be tested and iterated to meet high quality control standards. Once validated, it will be ready to scale globally across sectors.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响/商业潜力是使经济发展援助组织能够规划，实施，衡量和实现更好的性别平等和社会包容成果。两性平等被认为是促进发展和使社区摆脱贫困的一个重要因素。增强妇女权能有助于健康和富有成效的家庭、社区和国家。这样做的一个重要步骤是将高质量和及时的性别分析（审查性别角色、活动、需求和机会的差异如何在具体情况下影响男子、妇女、女孩和男孩）纳入决策和项目规划。对公共和私营部门而言，及早进行注重行动的性别分析对于解决问题和改善成果至关重要。2015 - 2016年，经合组织援助机构平均每年花费417亿美元用于性别平等和妇女赋权。据保守估计，这一支出的3-5%用于性别分析和行动规划，仅发展部门的市场就达13 - 21亿美元。这个小企业创新研究第一阶段项目将开发和测试一个基于网络的应用程序，使目前进行性别分析的手工程序自动化。这解决了援助组织面临的一个真实的世界性挑战，即有效地将性别分析纳入规划，以便为有效和及时的决策提供信息。尽管这是许多组织的一项要求，但采购和合同拖延、性别问题专家短缺以及手工研究和数据收集等问题仍然存在。 该项目将开发一个机器学习模型，该模型利用大数据，API和文本挖掘，由专家创建的分析框架驱动，以自动化这一过程，并以一小部分成本立即提供定制的结果。第一阶段将为一个部门和选定的国家建立、培训和测试模型。到第一阶段结束时，将对该模型进行测试和迭代，以满足高质量控制标准。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。