Health & Fitness App For Building Predictive Analytics Module

Overview


Industry: Health & Fitness

Services: AI & ML, Web & Mobile development, Product Engineering

Year: 2020

One Of Top Health & Fitness Industry

The Client provides user-friendly and customized applications in the domain of health and fitness. To improve the quality of nutrition, sleep, physical activity and mental peace, over 75M users globally are using the specially designed apps across platforms. The Client wanted to improve the quality and efficiency of the apps through the help of predictive analysis and for this they needed a reliable and competent service provider in the field of AI and ML.

Introduction

About Project

The client strongly believed that personalized content is the game changer in health and fitness applications. Using the data from the customers and running the data through several models already in place can significantly generate personalized recommendations and solutions to cater to health and fitness requirements of the user.

Validating the hypothesis for a business case

The client strongly believed that personalized content is the game changer in health and fitness applications. Using the data from the customers and running the data through several models already in place can significantly generate personalized recommendations and solutions to cater to health and fitness requirements of the user.

Building a Proof of Concept and Challenges

  • The existing system needed a revamp so that the users can be provided with additional guidance on their personal health and lifestyle apart from the general guidance that is available almost everywhere.
  • The process of data acquisition and analysis done, formerly, was very conventional and it was a challenge for our team to provide an end to end business intelligence (BI) solution and declutter the process.
  • The revamped AI-based health and wellness app was expected to support handling large amounts of user data collected from user activities and stored in the database of the client. This also required the need of cloud integration to make the data available on the go.
  • Creating a predictive model that would generate recommendations on health and wellness based on individual user data sets was a big challenge and it required several hours of input from our scientists.

Solutions

The existing database design and data quality was inefficient for analytics. Metricoid team conducted migration of entire data from the client’s database to inhouse storage and revamped the database structure of the client accordingly.Our next step was to work on data visualization by mapping out the tables of data. As a raw data storage, there was a Couchbase cluster. For a reliable data transfer to BI data warehouse (DWH) we added Kafka , i.e. PostgreSQL, using Spark procedures. To provide interactive dashboards, we used Apache Superset on top of BI DWH.
As per requirements of the client, a solution was needed wherein the data analysts and marketing managers the option to select from different filter parameters such as:

  • Gender
  • Height
  • Weight Gain/Loss
  • BMI
  • Age
  • Type of platform used to run the app
  • Payment method preferred
  • Other interactive filters like time spent and goals set.

To enable a higher personalization level, several dashboards were included.

  • To allow the existing app to deliver personalized recommendations, a major challenge was to create a recommender system using Machine learning and predictive model. The ML based model was trained based on the data that users share through their profiles. A user enters basic personal data after downloading and installing the app, and the algorithm chooses a best-suited model and assigns a plan from the data provided.

    Also, we have built a tree-based recommender system and associative rules mining using Apriori algorithm, all written in Python. Depending on a user’s fitness level, automatically generated recommendations differ. If personal data suggests that a user is not able to cope with the current set activities, the system can recommend repeat workouts at the current level otherwise it can recommend higher level workouts.

    The client provided all the data for training. One major source of data gathering was from GPS provided it is allowed by a user and other data were based on the user activity and inputs.

Technology Used

Project Results

    • Positive AI validation

The Metricoid team has enhanced the existing mobile fitness apps of the Client with predictive analytics capabilities.

    • The Client benefited from cooperating with Metricoid in the following aspects

1.More personalized customer experience compared to the initial capacity of the app Better data processing and storage

2.Predictive analytics capabilities

We offered the Client to use state-of-the-art approaches and technologies to provide sought after services and scale up the number of customers.



Related Case Studies


Advertisement Efficiency & Conversion Rate Increase By AI

The Client presumed AI could help create a more predictable and scalable business model and wanted to prove this before going all in with a company-wide adoption.

VIEW DETAILS

API-first Digital Integration In Existing Ecosystem Of The Logistic Company

The client requested for a digital ecosystem with consolidated API integrations that can accelerate onboarding, provide real-time integration dashboards for shippers, carriers and logistic providers, resulting in minimal manual intervention and improved revenue infow.

VIEW DETAILS