Intervention Modeling Reference Document

Maize Production Intervention Modeling with NPK+20% Scenario Visualizations.

Note: The visualizations were created using Tableau Public. The embedded dashboards are provided for reference. Please click the listed titles to open each visualization in a separate tab.

  • Date: October 14-15, 2025
  • Venue: J N Tata Auditorium, IISc Bangalore

WebSciX India is a proposed satellite event of the ACM Web Science Conference, dedicated to advancing the interdisciplinary study of the Internet, World Wide Web (WWW), and Artificial Intelligence (AI) and their impact on human lives in India and surrounding regions. WebSciX builds upon the Web Science for Development (WS4D) series of events conducted in India since 2019.

WebSciX 2025 is a community-building workshop intended to build a strong core technical committee that can organize the annual WebSciX conferences. WebSciX 2025 is hosted as a co-located track at the Symposium on Data for Public Good, organized at IISc Bangalore, between October 14-15 2025.

UP – Urban – Secondary Dropouts

Schools which teach class 6 – 8 in Urban Uttar Pradesh were considered

Based on the analysis, the following are deduced:

Lower Dropouts Higher Dropouts
Higher percentage of Private SchoolsHigher percentage of Minority Schools
Hindi as medium of instructionUrdu as medium on instruction
Good ClassroomsTeachers who are not graduates

In some of these factors, the heatmaps of dropout and factors are very similar, in some the visual difference in not striking, hence we have also included a scatter plot which displays the effects of the factor

UP – Rural – Secondary Learning Outcomes

Schools which teach class 6 – 8 in Rural Uttar Pradesh were considered

Based on the analysis, the following are deduced:

Better Learning Outcomes Lower Learning Outcomes
Good ClassroomsHindi medium
Schools with ElectricitySchools with lower internet connectivity
Any female above yrs of age having attended schoolMore Government Schools

In some of these factors, the heatmaps of dropout and factors are very similar, in some the visual difference in not striking, hence we have also included a scatter plot which displays the effects of the factor

UP – Rural – Secondary Drop out

Schools which teach class 6 – 8 in Rural Uttar Pradesh were considered

Based on the analysis, the following are deduced:

Lower Dropout Higher Dropout
Classrooms in Good conditionFrom districts with lower GDDP/ GSDP
Higher percentage of Female teachersTeachers Qualification Below Graduate
English medium as first languageHindi medium as First Language

In some of these factors, the heatmaps of dropout and factors are very similar, in some the visual difference in not striking, hence we have also included a scatter plot which displays the effects of the factor

District wise infographics

We also have a district wise sensitivity – so as to enable bird’s eye view of the major contributing factors in each district

Uttar Pradesh – Rural Primary – Learning Outcomes

Schools which teach class 3 – 5 in Rural Uttar Pradesh were considered

Based on the analysis, the following are deduced:

Better Learning OutcomeLower Learning Outcome
Regular Government TeachersChildren who are under weight
Any Female above 6 years ever attended schools Children who are stunted
Classrooms in good conditionMore enrollment in Government Schools

In some of these factors, the heatmaps of dropout and factors are very similar, in some the visual difference in not striking, hence we have also included a scatter plot which displays the effects of the factor

उत्तर प्रदेश

शिक्षण की गुणवत्ता और ड्रॉपआउट दोनों को संबोधित करके शैक्षिक परिणामों का रूपांतरण

डेटा विश्लेषण का दायरा

2 मिलियन से अधिक डेटा पॉइंट्स का विश्लेषण, जिनमें शामिल:
• 75 ज़िले
• 2.55 लाख विद्यालय
• 5.76 करोड़ छात्र
• अनेक डेटा सेट, जैसे UDISE, NFHS, SECC, ASER, यूपी सांख्यिकी

भाषाई परिदृश्य
उत्तर प्रदेश की प्रमुख बोलियाँ हैं — अवधी, बघेली, भोजपुरी, ब्रज भाषा, बुंदेली, खड़ी बोली, और कन्नौजी।

जनसांख्यिकीय और आर्थिक मुख्य बिंदु

  • अनुमानित जनसंख्या: 24 करोड़, जिनमें 70.6% ग्रामीण क्षेत्रों में
  • 2023–24 के लिए अनुमानित GSDP: ₹27,000 करोड़

माध्यमिक शिक्षा में कम ड्रॉपआउट दर के शीर्ष 3 कारण
ग्रामीण क्षेत्र:

  1. कक्षा VI–VIII में बेहतर सीखने के परिणाम
  2. महिला शिक्षकों का अधिक प्रतिशत
  3. प्रथम भाषा के रूप में अंग्रेज़ी माध्यम

शहरी क्षेत्र:

  1. निजी (अनएडेड) स्कूलों का अधिक प्रतिशत
  2. अच्छे कक्षाओं का बेहतर प्रतिशत
  3. प्रथम भाषा के रूप में हिंदी माध्यम

माध्यमिक शिक्षा में अधिक ड्रॉपआउट दर के शीर्ष 3 कारण
ग्रामीण क्षेत्र:

  1. प्रथम भाषा के रूप में हिंदी माध्यम
  2. शिक्षकों की योग्यता स्नातक से कम
  3. सरकारी स्कूलों का अधिक अनुपात

शहरी क्षेत्र:

  1. प्रथम भाषा के रूप में उर्दू माध्यम
  2. शिक्षकों की योग्यता स्नातक से कम
  3. अल्पसंख्यक स्कूलों की अधिक संख्या

बोली के अनुसार ग्रामीण प्रगति के पैटर्न

खड़ी बोलीभाषी ज़िले (पश्चिमी यूपी): ग्रामीण क्षेत्रों में मजबूत सीखने के परिणाम लेकिन शहरी क्षेत्रों में ड्रॉपआउट का अधिक जोखिम, संभवतः औद्योगिकीकरण और नौकरी पलायन के कारण।

भोजपुरीभाषी ज़िले (पूर्वी यूपी): ग्रामीण क्षेत्रों में मजबूत सीखने के परिणाम लेकिन शहरी क्षेत्रों में ड्रॉपआउट अधिक, संभवतः शिक्षा या रोजगार के लिए शहरी क्षेत्रों या अन्य राज्यों में पलायन के कारण।

अवधी भाषी ज़िले : राज्य के लगभग मध्य भाग में स्थित, जिसमें कानपुर, लखनऊ, अयोध्या, प्रयागराज जैसे शहरी मिश्रण वाले क्षेत्र शामिल हैं। ग्रामीण क्षेत्रों में औसत सीखने के परिणाम दिखाई देते हैं, लेकिन शहरी क्षेत्रों में यह प्रवृत्ति काफी सुरक्षात्मक है, जहाँ अनेक निजी शैक्षणिक संस्थान और सरकार द्वारा प्रदत्त मजबूत शैक्षिक अवसंरचना मौजूद है।

UP – Rural Primary Schools – Dropout

Schools which teach class 3 – 5 in Rural Uttar Pradesh were considered

Based on the analysis, the following are deduced:

Lesser Dropout rates were absorbed in the following:

Less Dropouts More Dropouts
Schools with good ClassroomsChildren who are stunted
More Female teachersDistricts which have low GDDP / GSDP
English as medium on instructionMore Government Schools

In some of these factors, the heatmaps of dropout and factors are very similar, in some the visual difference in not striking, hence we have also included a scatter plot which displays the effects of the factor

SDG 4: Quality Education


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.

Predictive Impact Analysis – Wheat Yield

Wheat Factors

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)

Predictive Impact Analysis

Chat Icon