MyDataSay Android App for Predictive / Deep Learning Model Deployment / Download

MyDataSay is an Android App for deploying predictive / deep learning models on Android devices such as phones and tablets. It provides a simple easy way to deploy your predictive / deep learning models for people who need heuristic information from your past data. Note that predictive / deep learning models are developed using CMSR Data Miner / Machine Learning / Rule Engine Studio from your historical data such as insurance claims data, credit delinquency/default records, etc.

Predictive models are developed from CMSR Studio using methods described in the following links;

• Credit Risk Analysis, Risk Scoring and Predictive Modeling
• Insurance Risk Analysis, Risk Scoring and Insurance Claims Predictive Modeling

To download the App, click MyDataSay Download. It's a .zip file. Read the "USER-INSTALL-GUIDE.txt" for installation on your Android devices. Android 4.0.0 or newer versions are supported. Web-server version is also available. For information, please read Rosella BI Server.

The following screenshots show how end users will use MyDataSay Android App;

(MyDataSay Screenshots)

1. User enters model input data as in the following screen and
click the "Evaluate" button;

2.Then the model shows the following results;

3. User clicks "About Model" to assess the prediction.
The following information is displayed. It provides information how
the result can be interpreted. Note that this can be heard with
speech interface. Just press the "Speak" button.

4. Non-RME models provide graphical visualization of models.
User clicks "Visualize" to understand how the prediction is made.
The following screen shows neural network internal status. It shows how
the result is produced;

The following screen is decision tree internal status. It shows how
the result is produced in decision tree;

To download the App, click MyDataSay Download. It's a .zip file. Read the "USER-INSTALL-GUIDE.txt" for installation on your Android devices. Android 4.0.0 or newer versions are supported. Web-server version is also available. For information, please read Rosella BI Server.