We are helping a leading NGO with AI and ML-based applications and solutions to improve their content and operational processes.
The escalating demand for fast and personalized service is keeping retailers on their toes. The best way to stay ahead of competitors and deliver prompt customer service is by automating the manual processes. By automating processes, retailers can reduce the risk of manual-errors and therby improve the efficiency.
To democratize the education in the rural levels, the client distributed ‘smart-tablets’ with an inbuilt learning app for community-level interaction in a few villages. Initial insights into the grass root-level interaction lead them to expand their testing scenarios to the higher community level in rural areas. The client wanted to understand the content/subject consumption when students were given free access to learning. Information gathered about the content consumption would then help them develop better content ahead and improve student engagement.
The client could not zero-in on the exact groups of students who accessed the app on the tablet or even the content that worked well within these groups. Categorizing them into any specific cluster was not feasible without the help of deep analytical insights.
Data collected from each tablet was housed in a local server that would record the multiple variables needed to analyze the data. Various data sets such as the subjects, quizzes, time logged in, engagement levels, etc., were recorded to get an understanding of the overall effect of the smart-tablets distribution.
Voluminous data generated did not have any pattern for easy comprehension and implementation of new strategies to improve engagement. Impact Analytics performed extensive exploratory data analysis and clustering to understand trends in the data.
The data was clustered using K-means clustering on group level and content level. The group level clustering involved clustering segments/groups based on engagement with the tablet. Content level clustering was based on the content consumptions from the app. Before grouping, the data had to be cleaned and normalized. All the data obtained was normalized to one scale to carry out proper analysis and provide accurate results. Following variables were used for clustering:
Days in a month
- The average number of days the app was accessed in a month by a group.
- The metric was divided by 30 days to normalize the variable.
- The total number of resources accessed by the group in their history as a percentage of the total number of resources available to the group.
Time spent on the app
- The total time spent on the app per day (in seconds)
- The variable was normalized by dividing by 86400 (no. of seconds in a day).
Impact Analytics’ analysis of customer behaviour and product preferences, and strategies for customer segmentation and risk identification enabled the client to considerably reduce attrition by 22%.
The resulting churn reduction delivered an incremental 4% top line growth to the next quarter.
Intervention strategies recommended by Impact Analytics and deployed by the client ensured retention of high value customers.