SBIR Phase II: The Smart Study Recommendations Engine

这个小企业创新研究（SBIR）第二阶段项目可能会提高学生的成绩。在美国高等教育机构中，每年大约有470亿美元用于2200万学生的学术支持。当一个孩子在讲座结束后遇到困难时，以往的帮助都是通过导师和家庭作业热线提供的；这些途径可能不足以弥补学生离开教室后的学习差距。预计智能学习推荐引擎将进一步普及家庭作业辅导和课外学习辅导。作为一个点对点平台，这项技术可以减少个性化作业和课堂外帮助的成本，使学生能够按照自己的时间和节奏学习。该平台旨在特别影响来自经济或社会挑战背景的学生。该项目的目标是帮助世界各地所有学生更容易获得、更普遍、更包容的学业成功。这项技术最初是在美国的学院和大学部署的，目标是实现全球影响。这个小企业创新二期项目从互联网学习资源中收集数据，分析资源以获得预测性见解，并自动提供广泛的、同行评审的、个性化的学习材料，帮助学生缩小学习差距，而不需要学生进行复杂的互联网搜索。该项目还将为学生提供与有能力的同龄人联系的能力，他们可以通过倾听他们的问题和提供更深层次的主题清晰度来提供额外的支持。该公司正在使用机器学习作为基础技术来启用智能学习推荐引擎。该奖项反映了美国国家科学基金会的法定使命，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。

This Small Business Innovation Research (SBIR) Phase II project may improve student achievement. Within U.S. higher education institutions, $47 billion per year is spent on academic support for roughly 22 million students. When a child struggles after a lecture ends, help has historically been delivered by tutors and homework hotlines; Those avenues can be inadequate in closing learning gaps for students after they exit the classroom. The Smart Study Recommendations Engine is expected to further democratize homework assistance and help with studies outside the classroom. As a peer to peer platform, the technology may shrink the cost of personalized homework and out of classroom assistance, enabling students to proceed at their own time and pace. This platform seeks to especially impact students from economically- or socially-challenged backgrounds. The goal of the project is to help make academic success more attainable, common, and inclusive for all students everywhere. The technology is initially being deployed in U.S. colleges and universities, with the goal of achieving a global impact. This Small Business Innovation Phase II project harvests data from internet study resources, analyzes the resources to surface predictive insights, and automatically delivers wide-ranging, peer-reviewed, personalized study materials to help students close learning gaps, without requiring the students to perform complex internet searches. The project will also provide students with the ability to connect with capable peers who can provide additional support by listening to their issues and providing deeper subject clarity. The company is using machine learning as the underlying technology to enable the Smart Study Recommendations Engine.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.