This SBIR Phase I project will fund development and release of a new way of using big data to maximize educational outcomes and the potential of each individual child. The project will create individualized learning paths for every student that dynamically adjusts based on their abilities across thousands of educational topics. The engine adjusts up to find their maximum potential regardless of age or grade, and adjusts down when they are struggling. The simple, yet engaging, games combined with gamification elements will keep the child wanting to play over and over, constantly learning as they go. The project will provide a tool to parents looking to enhance their child?s education as well as to those that prefer to homeschool. It will also be a powerful teacher's assistant, able to monitor the progress of each child in the classroom so the teacher can better monitor and manage progress of their student base. The Parent and Teacher Portals will connect the classroom and home learning experience and allow both parents and teachers to see how each child is performing and where they need to intervene to help. Over time, the project will test and deploy new ways to learn. The potential commercial market for this product includes parents, homeschoolers, and teachers. The initial target market is kindergarten to 8th grade. The project will improve education outcomes at these crucial ages. The project uses patent-pending technology that combines a set of probabilistic engines to determine the right content for each student based on their individual ability. It does not determine content based on their age or grade and makes no assumptions about what the student can or can?t do. Instead, it allows the student to set their own limits and use Big Data to predict and test optimal learning paths. The learning engine can work with any category of educational content and deliver that content dynamically to any type of game. The project can measure the learning impact by making changes to the traditional learning paths within clusters of students. It will uncover if, for example, fractions should be introduced earlier to all children, or subsets of children. As opposed to the option of skipping a grade or being held back, a student doing well (or poorly) could be in the same class with their peers and still have unique content that challenges them and maximizes their natural abilities. The learning engine will use business intelligence techniques to identify problem areas for each child and recommend what to practice and practice techniques. The project team has previously received patents on technology in the gaming industry, and is confident in the ability to receive a utility patent for this technology for intellectual property protection.
