Virus-proof early homeschooling

Millions of children were confined during the pandemic. Parents working from home were often unable to dedicate time to teach their first graders to read and write.

The solution is a subscription delivering educational devices to teach 3-6 year old children reading, writing and math with little intervention. It comprises puzzle games with letters and numbers in wood and plastic so children memorize the shapes of the letters while having fun. It also has an Artificial Intelligence that teaches children decoding strategies and reading. We have a patent pending for this invention.

At scale and with our "buy one give one" model and a partnership with organizations prominent in women and girls' education in emerging countries, our solution could improve education and literacy for millions and have the most impact through the female influence on the community.

Children learn reading, writing, and basic math with considerable human involvement, with about one year of contact time with a qualified teacher. This educational model works and has been proven for hundreds of years, but it has two problems.

First, it perpetuates social inequality within western countries, as high-quality teachers prefer to teach in high-quality schools attended by children from privileged families, and children from disadvantaged backgrounds learn from lower-rated teachers. Children from privileged backgrounds gain a considerable head start that persists through adult life. Low early literacy decreases wages and educational attainment (see Elango et al., 2015) and increases health care costs (see Concordia University).

Second, it perpetuates social inequality between countries, as emerging countries lack qualified teachers to provide a good education (Deon Filmer found that "fewer than 3 percent of teachers in Mozambique, Nigeria, and Togo can competently grade homework based on the curriculum they teach"), and without a good education the next generation of teachers will also lack competency.

Early childhood interventions have very high returns of 7-10% per year (Elango et al. 2015). The flip side of this result is that children who don't receive good interventions will lag significantly behind.

The solution is weekly subscription of literacy puzzles and toys, customized and appropriate for a child's age and "zone of proximal development." All together, it constitutes a self-contained system to teach 3-6 year old children reading, writing and math without little intervention. The first puzzles spell names relevant to the child's environment: the child's name, names of family members, and other words chosen by parents. At four years of age, children start receiving individual letters to form any word, numbers to learn to count, and math symbols to learn arithmetic. All of these toys interact with an artificial intelligence (either a tablet application or a server box that we manufacture) that teaches children reading, writing, and maths. Children speak a word they want to learn, the software recognises the word, and shows its spelling on the screen. Children form the word with the letter blocks, the software recognizes the word and pronounces it, so children learn to explore the language at their own pace. The software teaches decoding strategies relevant to the child's progress. Children learn to count with a similar system; and learn to write with purpose-built tactiles toys.

We serve two distinct populations. In western countries, parents with children in closed schools or concerned about their child's progress subscribe to receive our toys every week. Children can learn on their own, are less likely to fall behind on learning, and parents have more time for themselves.

In emerging countries, we partner with expert organizations in serving women and girls. We chose girls because, similar to early childhood education, that is where an investment begets the most impact. We provide these organizations with the same number of devices that we sell ("buy one, give one"). We also offer the option for the children to be in contact and become pen-pals.

Education is the strongest predictor of a child's future prosperity. Although gender differences are small for 4-7 year olds, early childhood is the period when investments pay the most dividends and thus a prime occasion for significant lifelong impact.

Although we have been focused on exploring and finding product-market fit, we strongly believe that this product could improve access to learning for marginalized children, e.g. those living in remote villages or in refugee camps. We also believe that investing in girls' education has large multiplier effects in significantly and lastingly improving their communities (Camfed Impact Report, 2010)

The toy innovates by merging a physical toy appropriate for young children with the flexibility of software to teach them literacy. Many tablet applications that help with literacy are all-digital and unsuitable for very young children.

The dual physical and virtual aspects allow children to play with a physical toy that evolves with them. For example, the toy teaches decoding strategies to children appropriate for their age and previous experience, so children are always learning new strategies. Children can explore the language, e.g. they can use the wooden and plastic blocks to form a word that does not exist, such as "wugs", press a button on the server box, and an artificial intelligence synthesizes the pronunciation of that word from having digested a phonetic dictionary of the language. To play with words, the artificial intelligence proposes new words from the letters: for example, if children form "nod", the system proposes "node" with a new letter or "done" with a new letter and a rearrangement of letters in increasing complexity. To teach maths, children can form equations such as "1+1=2" and the system provides feedback on whether it is correct.

We made many improvements based on children's feedback, e.g. that some letters like the S need to be symmetric to avoid frustration. Our extensive testing leads us to believe that the physical part of the toy is now feature complete and we have applied for a patent.

The solution uses software and technology at every stage of the product. For the hardware part, the choice of letters is optimized with linear programming to the most common words in children's books of the target language. From this choice of optimal character combinations, software automatically generates the design files for Computer Assisted Manufacturing. Fabrication is digital with computer-numerical control (CNC) laser-cutter and router. The hardware is all streamlined to keep costs low. At scale, the molds for the pieces will be machined to drive costs even lower and save on material.

The software part is where we most excel at technology and we will continuously improve. Computer vision methods (such as edge detection, histogram equalization, and contour simplification) and machine learning methods (nearest neighbors and neural networks) serve for optical character recognition. Neural networks serve for speech recognition, which are pre-trained on massive datasets and that we fine-tune for children's voices on a small dataset. Speech synthesis allows the software to communicate with the students. Neural networks also serve to digest a full dictionary with words and phonetic transcriptions and synthesize the pronunciation of new words. This part has fixed costs and can be deployed at zero marginal cost, which also means that any improvement can affect every single user with updates.

The technologies we use in the artificial intelligence are well-proven: speech synthesis (text-to-speech) to sound out words and read out text in a natural way (especially with WaveNet voices), speech recognition (speech-to-text) to identify spoken words as in digital assistants, computer vision to recognize letters (and at its best, used in self-driving cars), and deep learning (and I have done research in neural networks, see https://arxiv.org/abs/2001.11396).  The technologies we use in manufacturing are also well-proven: Computer Assisted Manufacturing (with software such as LaserCut Pro or VCarve Pro), Computer Numerical Control (e.g., laser cutters routers from Laserscript), and other methods of digital fabrication (such as the Computer Numerical Control model mill and 3D printers). The innovation comes in the combination of these technologies and its application to early literacy, especially the interplay between physical and tactile toys and software to recognize those toys and teach literacy, and we file a patent for this innovation ( https://www.ipo.gov.uk/p-ipsum/Case/ApplicationNumber/GB1910475.1 ).

Our theory of change comes in five steps. The challenge we address is the difficulty of early literacy after the pandemic. The activity we undertake is to produce, market, and refine a self-contained system for children to learn reading, writing, and math. The output is the public face on our website and the partnerships we want to forge with organizations working in female education. The outcome that we measure and our "north star metric" is the number of subscribers. The impact goal we would like to measure is the improvement in literacy due to the toy.

Our outcome at the moment consists of 17 families using the kit (at different stages). One of them said:

"The big advantage is that our children can already identify letters and the
correspondence of case. For example, they know that "i" and "j" come with
dots. We expect that they it will be much easier for them to learn to read."

The big unknown in our theory of change is the connection from output to outcome to impact goal. To address this, we want to partner with the University of Cambridge (where the founder did a post-doc in early childhood education) and with the Education Endowment Foundation to run a randomized controlled trial of the benefits of the toy in standardized scales, such as the Bayley Scales of Infant and Toddler Development, and use academic studies to extrapolate from those scales to other children's outcomes, such as literacy and likelihood to read at grade-level.

We are currently serving children in 17 families. In one year, we want to be serving 150 families in western countries and partner with one organization working on women and girls' education in emerging countries. In five years, we want be serving one million children by partnering with a public school system such as the province of Québec, the New York City public school system, or the entire French public kindergarten system.Over the next year we want to pilot a project in 5 schools with 150 children total, incorporate the lessons from the pilot into the randomised control trial (performed by external academic partners) over two years to gauge the effectiveness of the solution, and use the results from the trial to sell to the large organisations we want to reach in 5 years.

Over the next year we want to become profitable with our subscription product in western countries. Within the next five years, we want to set up a randomized control trial (performed by external academic partners) over two years to gauge the effectiveness of the solution, and use the results from the trial to serve the large organizations we want to reach in 5 years.

Over the next year, the main barriers are finding product-market fit and growing our early adopters. Over the next five years, the main barrier is being ready for the randomized control trial because early childhood education takes several years to show results, so the trial must be ready by year 2 if we want results by the start of year 5.

Regarding the product-market fit, we have been accepted in an incubator that grew out of the pandemic and have received valuable mentorship as we keep iterating with our product and business model. Regarding the randomised control trial, I have a network of researchers from my previous career in academia who specialise in early childhood education and a list of several grant bodies with programs to fund rigorous evaluation of innovative solutions in early childhood education, such as the Education Endowment Foundation in the UK, which also offers support in taking positive approaches to the national level.

One person (founder and project lead), working on this solution now full-time with freelancers for intellectual property law and typeface design.

I hold a Bachelor of Science in Computer Science from Ecole Polytechnique (France) and a PhD in Economics from Columbia University. I did a post-doc in Economics at the University of Cambridge focused on early childhood education and another post-doc in software engineering and artificial intelligence at The Alan Turing Institute. I am passionate about children's education and have invented several toys, devices, and games. I also enjoy digital fabrication with graphic design and computer-assisted manufacturing. I am committed to open-source software (see my Github repositories at github.com/miguelmorin and my contributions on StackExchange @mmorin) and decided to file a patent for the sustainability of the business. I am also passionate about languages (speaking fluently Portuguese, French, English, Spanish, and having passing knowledge of German).

We currently use the services of Microsoft Cognitive Services and Google Cloud Platform for speech recognition and speech synthesis. We will develop our own system that can work without an internet connection. We work with them with automated queries to their Application Programming Interface.

We provide products and services to parents of children between 3 and 7 years of age who decided to keep their children at home because of the pandemic or who are concerned about their children falling behind on early literacy. We show our commitment to social causes with a "buy one, give one" model, where we supply the same number of our products to parents who can afford it and parents who cannot (for the latter, we rely on partnerships with organizations with the relevant expertise of girls' education in emerging countries).

We have personal savings to cover two years of operation and are also applying for grants for the early years. Financial sustainability afterwards will be from customer revenue, which is the best way to stay in business.

I have spent 10 years in academia, where thinking is narrowly defined, delimited with specific steps, and mostly negative in the sense that people shoot down ideas to see which ones survive. I would benefit from interacting with creative thinkers, optimists, and courageous creators who are not afraid to take on challenges. I have made big leaps in my solution thanks to feedback from other people and I expect I will benefit even more from this world-class selection of talent in pivoting my business model or improving the product. We would also benefit from the exposure to recruit skilled and committed people into our team when we are ready to grow, and possibly also to find partners from the Solve network that share the vision of the sustainable goal 4, quality education for all. And we would also benefit from the financial stipend.

We would especially like to partner with organizations supporting early learning for girls in emerging countries to benefit from their expertise, which would take us decades to replicate. We would also like to partner with any organizations that have expertise in supporting early learning, or in running early childhood interventions.

The self-contained learning system could work well in refugee camps where children are out of school. We would use the prize to partner with a refugee reliefe organization and run a pilot study of the impact of the solution in refugee camps.

Our solution has got a lot of interest from schools and organizations that work with children with disabilities because it is tactile and it allows children to learn without screens. It could work well for children with visual impairments, or children with autism who prefer to learn alone. As one executive put it, "I've never seen anything like it, your product can remove many barriers to learning." We would use the funding to fund a pilot study with an organization in the field of disability learning for girls.

When we first trialled the product, we were surprised to see that adults enjoyed playing with the puzzles as much as children. For adults with low literacy, we envision that children and their parents or even grandparents would come together and play and learn to read as a family. We are already based in Portugal and plan to run pilot studies here.

We rely heavily on data science, machine learning, and artificial intelligence in our teaching technology (speech-to-text, text-to-speech, and computer vision). The founder has a track record in science (first in economics with publications at http://www.columbia.edu/~mm3509/research.html and then in deep learning with a paper on the lack of reproducibility in neural networks, at https://arxiv.org/abs/2001.11396).

Our company is a hybrid of non-profit and for-profit, and we have the potential to impact thousands of children in western countries that move in and out of the coronavirus lockdown, millions of children in western countries who cannot afford quality childcare, and also millions of children in the developing world who lack access to good teachers.