Adverie
The New Way To Target Ads At Consumers.
Consumers passing by a digital banner in a mall or another location with ADVERIE software installed will be able to see the most relevant and customized advertisements based on their physical characteristics and types of equipment, increasing their interest in the ads and lowering the cost to the advertising company because they only have to pay for the duration of the display when they have the targeted audience. The firm will save money on advertising by not paying for periods when there is no audience to see the advertisement. Aside from this advertising, ADVERIE will also collect public feedback based on the passer's state reactions and other characteristics such as the duration of the passer's involvement with the banner, and send it to the advertising company's analytics field to improve their services or advertisement. The program would lessen public involvement in viewing advertisements in physical areas since they would not need to involve themselves to see their desired advertisement. Making the consumer experience more pleasant reduces the time between noticing and acquiring the product, which also benefits the advertising business.
Presentation
-
Features
Based on age, mood, gender, location, and body posture, the application will be able to propose the following advertising to a user.
- Predicts user's Age, Mood, Gender
https://github.com/justadudewhohacks/face-api.js - Objects Detection
https://github.com/tensorflow/tfjs-models/tree/master/coco-ssd - Body Segmentation
https://github.com/tensorflow/tfjs-models/tree/master/body-segmentation - Pose Detection
https://github.com/tensorflow/tfjs-models/tree/master/pose-detection
Tech Stack
Client: React, Redux, MaterialUI
Server: Node, Express
Packages: react-advertising, create-react-app
Models: ml5.js, TensorFlow.js
Roadmap
- Developing a React app with minimal UI
- Integrating 4 pre-trained models from ml5 and TensorFlow.
- Integrating Facebook ads using ads library api
https://www.facebook.com/ads/library/api/
Feedback
If you have any feedback, please reach out to us at adverie.help@gmail.com
Log in or sign up for Devpost to join the conversation.