Obesity has tripled since 1975 and is projected to hit 15% of the World’s (and Singapore’s) population by 2024. We need to move beyond rewards-based daily steps trackers towards a better understanding of our customers. Public and Personal Health Insurance and Enterprise Industry Health Care costs are rising. Claims are rising, current knowledge of the customer is limited, and customers experience more “stick” than “carrot” when dealing with these industries. Yet insurance providers are looking for a way to better connect to their customers. We are developing an intelligent (machine learning) AI platform that will build on established behavioural science, intervention & change research and back-end data algorithms, to personalise each person’s activity and dietary preferences, as well as their motivational blue-print.
Model development, training and consumption Using Tensorflow and PyTorch machine learning frameworks. Utilizes Jupyter Notebooks on Amazon SageMaker, including Nvidia's CUDA and cuDNN drivers for popular deep learning platforms, Anaconda packages, and libraries for TensorFlow and PyTorch. Automatically tunes your model's hyperparameters to improve accuracy of predictions. Utilizes where possible, the optimized algorithms for customer segmentation analysis such as k-means clustering or principal component analysis (PCA). The intervention recommendation engine will also be built and deployed through this workflow. Other capabilities included are convolutional neural network (CNN) capabilities for Food AI development and recurrent neural network (RNN) & natural language processing (NLP) for text analysis. The machine learning models are consumed by the application via an HTTPS application programming interface (API) endpoint that is called from our Front End App.
This technology is applicable in the following industries: Insurance, Government and Enterprise Wellness Directly impacts the improved health of customers by an increased ability to retain them for longer, as the interaction provides more personal relevance to their lifetime goals. Improve the investment return in existing versions of corporate apps, due to deeper customer insights. Consumer Far greater success for customers goals (weight loss with improved activity levels) over other traditional health/fitness programs Far more personal - Evolves with continuous AI learning. Evolves with the customer’s health journey and lifestyle changes. Non-static & completely personal ensuring greater trust and adoption.
Existing one-dimensional health & fitness apps aren’t making a long-term difference to the user. 60% opt out after 6-8 uses 44% opt out due to data input requirements 57% state the non-personal nature of the apps do not motivate them Most apps cater to the active minority, and not the sedentary 80% Value to the enterprise include reduced costs through: Healthier customers = less claims Reduce claims processing costs [our app is able to direct customers to preferred medical / health providers] Increased customer retention, keeping them for longer Increased brand awareness, reaching out to existing & potential customers Enhanced “corporate citizenship” branding