Understanding the Web
This dashboard visualizes the relationship between student dropout rate and influencing factors using two key visual tools. The scatter plot illustrates the correlations between dropout rates and specific variables such as infrastructure, or teacher-student ratio, etc. The heatmap highlights how contributing factors vary across various regions in Karnataka. Together, these visuals help identify critical patterns and areas needing intervention.
You can select the variable for which you want to see correlation with wheat yield, from the dropdown menu.
If the p-value for a variable is less than 0.05, then that variable has a significant correlation with wheat yield.
It is found that the following factors have significant correlation with Wheat Yield
1. KCC(Kisan Credit Card) Distributed (+ve correlation)
2. Net Irrigated Area (+ve correlation)
3. NPK(Nitrogen Phosphorus Potassium fertilizer) Distributed (+ve correlation)
4. Regional Rural Bank Loans (+ve correlation)
You can select the variable for which you want to see correlation with rice yield, from the dropdown menu.
If p-value for a variable is less than 0.05, then that variable has significant correlation with rice yield.
It is found that the following factors have significant correlation with Rice Yield
1. Private Sector Bank Loans (+ve correlation)
2. Public Sector Bank Loans (+ve correlation)
3. NPK Distributed (+ve correlation)
4. Regional Rural Bank Loans (+ve correlation)
There are 3 components to the below dashboard:
In the Predictive Impact Analysis dashboard, we can see the impact of different factors on Student Drop-out Rate (SDR). We can intervene on a factor by selecting it from the dropdown menu and changing it by any amount (eg: +10% , -10%, etc) and we can see the corresponding changes in the rate at the district level.
In the Prescriptive modelling dashboard, we can set the target SDR and the model outputs the prescribed values of different factors to achieve the specified target SDR. We can also see the corresponding change in SDR at the district level by adopting these prescribed values of the factor. We can also see sensitivities of different factors which talks about the importance of the factor and it ranges from 0 to 1. If a domain expert deems a specific factor as unimportant, they can assign a sensitivity value of 0. For factors considered partially important, a sensitivity value of 0.5 can be assigned. If the expert believes the factor unquestionably plays a role, they have the option to set its sensitivity to 1.
In the prescriptive modelling dashboard itself, there is a box displaying the state stability score after an intervention. There is also a scatter plot showing the relation between impact and stability with districts represented as points.
Finally, the dashboard includes a feature for budget allocation. Positioned at the top is a pie chart derived from slopes obtained from multiple linear regression. The methodology systematically distributes the budget to address the requirements of various districts. Here, as well, we can see the sensitivities of the factors. If the policy maker/domain expert thinks that a particular factor plays no role, he can set its sensitivity value to 0 and the budget allocation model will automatically get re-adjusted.
I am currently pursuing Masters by Research in the Web Sciences Lab here at IIIT Bangalore. Prior to joining IIITB I have worked in Capgemini Engineering for three years as a Senior Associate and also worked as a Research Assistant in The Visual Conception Group Lab at IIIT Delhi. I am currently working on the Online Learning Navigator Project in partnership with Gooru Labs. My Research Interests are Optimizations in Machine Learning, Deep Learning and Vision Language Models.
There are 4 components to the below dashboard.
In Predictive Impact Analysis dashboard, we can see the impact of different factors on Maternal Deaths (MD). We can intervene on a factor by selecting it from the dropdown menu and change it by any amount (eg: +10% , -10% etc) and we can see the corresponding changes in MD at district level.
In Prescriptive modelling dashboard, we can set the target MD and the model outputs the prescribed values of different factors in order to achieve the specified target MD. We can also see the corresponding change in MD at the district level by adopting these prescribed values of the factor. We can also see sensitivities of different factors which talks about the importance of the factor and it ranges from 0 to 1. If a domain expert deems a specific factor as unimportant, they can assign a sensitivity value of 0. For factors considered partially important, a sensitivity value of 0.5 can be assigned. If the expert believes the factor unquestionably plays a role, they have the option to set its sensitivity to 1.
In the prescriptive modelling dashboard itself, there is a box displaying the state stability score after intervention. There is also a scatter plot showing the relation between impact and stability with districts represented as points.
Finally, the dashboard includes a feature for budget allocation. Positioned at the top is a pie chart derived from slopes obtained from multiple linear regression. The methodology systematically distributes the budget to address the requirements of various districts. Here, as well, we can see the sensitivities of the factors. If the policy maker/domain expert thinks that a particular factor plays no role, he can set its sensitivity value to 0 and the budget allocation model will automatically get re-adjusted.
