Enhancing Public Safety and Service Satisfaction – A Local Government’s NPS & Key Driver Analysis

Client Overview

A local government agency responsible for public safety, community services, and infrastructure faced declining public satisfaction based on Net Promoter Score (NPS) surveys. The agency had conducted periodic surveys to assess resident sentiment on safety, emergency response, public works, and other municipal services, but lacked the data-driven insights to:

1.

Identify the key drivers influencing public perception of safety and municipal services.

2.
Improve response times and service efficiency based on resident feedback.
3.
Enhance policy decisions  by leveraging data science to create targeted improvements.

The local government sought a data science-driven solution to analyze NPS trends, uncover key drivers, and implement changes that would increase community satisfaction while optimizing city resources.

Phase 1: Data Collection & Understanding the Public Sentiment

Survey Data & NPS Calculation

The local government had conducted surveys quarterly to gauge public sentiment on safety and municipal services. Questions covered:

$

Perception of safety (police presence, emergency response time).

$
Satisfaction with public works (street maintenance, lighting, waste management).
$
Trust in local government decisions.
$
Quality of emergency response services (fire, police, ambulance).
$
Public transport efficiency and accessibility.
From these surveys, NPS was calculated using the standard methodology:
$
Promoters (score 9-10): Residents highly satisfied with services.
$
Passives (score 7-8): Neutral respondents who were satisfied but not enthusiastic.
$
Detractors (score 0-6): Residents dissatisfied with municipal services.
The local government had an NPS of -10, indicating that more residents were detractors than promoters—a major concern.

Phase 2: Applying Data Science for Key Driver Analysis

The government agency partnered with BI Consulting Services to apply advanced data science techniques to extract meaningful insights from survey data and drive improvements.

Machine Learning-Based Key Driver Analysis

To determine the primary factors impacting NPS, we used:

$
Random Forest Regression: Identified the strongest predictors of high or low NPS scores.
$
Shapley Value Analysis: Quantified how much each factor influenced satisfaction.
$
Sentiment Analysis: Applied natural language processing (NLP) to open-ended responses.
Key Findings:
$
Emergency response time had the highest correlation with low NPS scores—a significant driver of dissatisfaction.
$
Street lighting & neighborhood cleanliness were secondary factors impacting safety perception.
$
Inefficient reporting of city maintenance issues led to frustration among residents.
These insights highlighted specific pain points that the government needed to address.

Phase 3: Implementing Data-Driven Solutions

1.

Improving Emergency Response Time

Predictive analytics for emergency dispatch optimization:

$
We used historical 911 call data to predict peak times for emergency incidents.
$
Machine learning models optimized police and EMS dispatch routing, reducing response times by 18%.

2.

Enhancing Public Safety Infrastructure

Smart street lighting project:

$
Sensor-driven adaptive lighting systems improved nighttime visibility.
$
Heatmaps from crime and NPS data helped prioritize street lighting improvements.

3.

AI-Powered Citizen Reporting System

AI chatbot & mobile app for complaints:

$
Residents could report issues in real time, linked directly to the public works department.
$
AI-driven ticketing prioritized urgent complaints (e.g., broken streetlights in high-crime areas).

Results & Impact

NPS increased from -10 to +15 in six months.

$

Emergency response time improved by 18%, boosting resident confidence.

$

Public works complaint resolution time reduced by 40%, leading to a cleaner, safer environment.

$

Crime perception improved by 22%, leading to greater community engagement with local government.

By leveraging data science, the local government transformed public sentiment, optimized resources, and enhanced safety across the city.