Customer Survey Analysis (Linear Discriminant Analysis)
Bot takes in the input data in a CSV file and performs the LDA algorithm-driven classification and provides output in the MS Excel.
Top Benefits
- Improves customer survey analysis process up to 25%.
- Reduced time with rule based grouping and augments quick decisions based on predictions from survey data.
- Provides high level of accuracy based on the quality of input data parameters.
Tasks
- Bot model could be used for dimensionality reduction in the pre-processing step.
- Bot model could be used for modeling differences in groups i.e. separating two or more customer classes.
Actions:
The Bot takes the CSV file and prepares the linear discriminant analysis and provides the output in Excel format.
Outputs:
Output: Result in the form of Excel. The output provides various customer groups.
Ex: Sample screenshots below shows the predicted class and whether the passenger is satisfied or not.
Free
- Bot Security Program
-
Level 1
- Applications
-
- Business Process
- Finance & AccountingHuman ResourcesSales
- Category
- Artificial IntelligenceInsightsProductivity
- Vendor
- Automation Type
- Bot
- Last Updated
- December 11, 2020
- First Published
- June 17, 2020
- Platform
- 11.x
- Community Version
- 11.3.1
- ReadMe
- ReadMe
- Support
-
- Nextgen Invent Corporation
- Mon, Tue, Wed, Thu, Fri 9:00-17:00 UTC+0
- 508-753-1512
- bot.support@nextgeninvent.com
- Bot Store FAQs
See the Bot in Action
Setup Process
Install
Download the Bot and follow the instructions to install it in your AAE Control Room.
Configure
Open the Bot to configure your username and other settings the Bot will need (see the Installation Guide or ReadMe for details.)
Run
That's it - now the Bot is ready to get going!
Requirements and Inputs
- Path: Path of the CSV file.
- NoOfColumn: Number of Columns in the CSV file.
- InputColumn: Header of the input columns of the CSV file.
- InputColumnDataType: Data Types of the input column (Available datatype: Numeric, String, Date).
- MissingNumberValueReplacement: By which value you have to replace the missing number values.
- MissingStringValueReplacement: By what string you have to replace the missing string values.
- IgnoreColumns: header of the Columns which you have to ignore in the model.
- Header of the Column on which you want to predict.