Industry: Web ads
Duration: 5 months
Team Included: AI engineer, React Native engineers, QA engineers, Project manager
Aterise developed a functional frontend system with an opportunity for further backend integration based on Customer’s mockup. The project resulted in a developed software which predicts people’s movements along the area which has beacons placed around. The software uses data taken from the accelerometer and user phone’s compass with the software set up on the phone.
Aterise received a task which was to create a fully functional MVP relying on the provided mockup by the customer. The prototype of the system contained 3 potential user roles: the administrator, the user, and the business user. Besides the opportunity to upload the examples of AI algorithms to the website, it was necessary to implement algorithms’ data verification system.
Aterise also set up a goal to develop a neural network algorithm, and thus, to increase the quality of customer service at hypermarkets and malls. Then customer created an alerting system for sellers. The system was based on the developed algorithm, and it functioned to inform that a potential client is approaching. Thus, the main goal was to create an algorithm which detects users moving around the mall.
Aterise turned the customer’s idea into reality and even exceeded the expectations as well as managed to cut down client’s expenses for the phase of frontend and backend integration. Milestone 2 was all about training the algorithm on the basis of the data received from the user’s device (cell phone). That resulted in the ability to predict user’s movements with an accuracy to 3 meters.
After that Aterise optimized the data, trained the neural network algorithm, and achieved prediction accuracy up to 97%. The company came to a decision to conduct a test check of the prepared solutions beginning from the simplest neural network algorithms and up to the most complex algorithms today. Thus, Aterise made the system operate fast and precise by creating an accurate and ideal algorithm.
Aterise turned Customer’s idea into reality and even exceeded the expectations as well as managed to cut down Client’s expenses for the phase of frontend and backend integration.
The customer received fully functional frontend system developed according to the latest trends and standards of web application development. The created neural network algorithm and its implementation let to increase the quality of customer service.