A collection of data analysis microprojects and case studies designed to explore real-world scenarios, enhance analytical thinking, and demonstrate practical data-driven problem solving across various contexts. Each project focuses on uncovering insights, testing hypotheses, and improving decision-making through data storytelling.
During July, TechX experienced a sharp downturn compared to previous months:
| Metric | June | July | Change |
|---|---|---|---|
| Total Sales ($) | 265,000 | 205,000 | −23% |
| Orders | 3,300 | 2,150 | −35% |
| Customer Rating | 4.6 | 4.1 | ▼ drop |
| Return Rate | 2.3% | 4.5% | doubled |
| Avg. Product Price ($) | 81 | 82 | slight ↑ |
👉 The decline was concentrated in Jordan (−40%), while Saudi Arabia & UAE remained stable, pointing to local or operational issues rather than a regional market collapse.
-
The company did not change prices or advertising campaigns during this period.
-
A new shipping policy was introduced at the beginning of July: free shipping is now only available for orders above $100.
-
The website experienced repeated outages (around 20 minutes daily for two weeks).
-
Customer service reports indicate a 60% increase in complaints about delivery delays.
-
In Jordan specifically, sales dropped by 40%, while Saudi Arabia and the UAE remained almost stable.
-
What are the possible reasons for the significant decline in July?
-
How would you connect the indicators together?
-
What additional data would you request to validate your hypotheses?
-
What recommendations would you provide to management based on your conclusions?
| Month | Total Sales (USD) | Total Orders | Avg. Customer Rating | Return Rate (%) | Avg. Product Price (USD) |
|---|---|---|---|---|---|
| JANUARY | 240,000 | 3,000 | 4.6 | 2.00% | 80 |
| FEBRUARY | 250,000 | 3,100 | 4.5 | 2.50% | 81 |
| MARCH | 255,000 | 3,200 | 4.5 | 2.20% | 80 |
| APRIL | 260,000 | 3,250 | 4.6 | 2.10% | 80 |
| MAY | 262,000 | 3,260 | 4.7 | 2.00% | 80 |
| JUNE | 265,000 | 3,300 | 4.6 | 2.30% | 81 |
| JULY | 205,000 | 2,150 | 4.1 | 4.50% | 82 |
- Shipping Policy Change (≥ $100 free shipping)
→ Drove away small/medium basket buyers (≈60% of Jordan orders). - Delivery Delays (+60% complaints)
→ Increased returns and lowered ratings. - Website Downtime (~20 min/day for 2 weeks)
→ Higher cart abandonment, lost conversions.
- Summer travel & holidays → Spending shifted to tourism/entertainment.
- Price & shipping sensitivity → Jordanian consumers more affected than Gulf markets.
- Competitor campaigns → Rivals offered “free shipping on all orders” in July, eroding share.
- Orders ↓ → Triggered by shipping threshold.
- Ratings ↓ & Returns ↑ → Driven by delivery delays + site outages.
- Jordan sales −40% → Seasonal travel + local sensitivity amplified internal issues.
💡 Insight: The shipping policy change was the critical tipping point, amplifying existing operational weaknesses and seasonal market pressures.
- Basket value distribution (<$100 vs ≥$100).
- Cart abandonment vs checkout completion during outages.
- Actual vs promised delivery times (SLA).
- Competitor shipping offers in July.
- Travel/tourism data for Jordanian consumers.
- Estimated revenue loss: ≈ $60,000 in July.
- Each −1 rating point ≈ −8% repeat purchase rate.
- Returns increase (+2.2%) ≈ −$4,000 monthly loss.
- Lower free shipping threshold in Jordan to $60–75.
- Launch “Trust Rebuild” campaign: free shipping on first August order.
- Emergency tech team → ensure zero checkout downtime.
- Introduce “Guaranteed Delivery” with compensation for delays.
- Improve UX: persistent carts, clear shipping costs upfront.
- Campaigns for returning travelers & back-to-school shoppers.
- Focus on sub‑$100 products to regain small basket sales.
- Build monitoring dashboard linking outages → cart abandonment → complaints.
- Dynamic shipping policies by country/season.
- Invest in stronger hosting & redundancy.
- Early‑warning system for spikes in complaints or sudden demand drops.
- Market intelligence unit to track competitor moves weekly.
The July decline in Jordan was not caused by a single factor, but by the interaction of policy missteps, operational weaknesses, and seasonal market dynamics.
Recovery requires immediate shipping policy correction, technical stabilization, and tailored market strategies.
📈 With urgent actions, 70–80% of lost sales can be recovered within 6 weeks.
CityCare Hospital experienced a sharp performance drop starting July, despite stable KPIs in the first half of the year.
Key issues included longer ER wait times, delayed elective procedures, rising readmission rates, and declining patient satisfaction.
| Month | Total Patients | ER Arrivals | Avg ER Wait (min) | Elective Admissions | Avg Delay (days) | Readmission Rate (30d) | Patient Satisfaction (1–5) | No-show Rate | Doctor-to-Patient Ratio (Day) |
|---|---|---|---|---|---|---|---|---|---|
| Jan–Jun | Stable growth | ~3,500 | ~40 | ~1,900 | ~1.2 | ~10.3% | ~4.5 | ~4.7% | 1:15–1:16 |
| Jul–Dec | Demand surge | ~4,400 | ↑ to 77 min | ↓ to ~1,620 | ↑ to 3.2 days | ↑ to 13.2% | ↓ to 3.6 | ↑ to 8.0% | 1:18–1:19 |
- Staff shortages (nurses & ER physicians) began in July.
- Imaging equipment downtime affected diagnostics.
- EHR system upgrade caused workflow slowdowns.
- Seasonal demand spike (heatwave + respiratory illnesses).
- Complaints increased by 48% starting July.
Analyze the root causes of performance deterioration, link indicators, quantify impact, and propose actionable recommendations to restore service quality and operational stability.
|
| Month | Total Patients | ER Arrivals | Avg ER Wait (min) | Elective Admissions | Avg Delay (days) | Readmission Rate (30d) | Patient Satisfaction (1–5) | No-show Rate | Doctor-to-Patient Ratio (Day) |
|---|---|---|---|---|---|---|---|---|---|
| JANUARY | 12,800 | 3,100 | 38 | 1,700 | 1.2 | 10.50% | 4.4 | 5.00% | 1:16 |
| FEBRUARY | 13,200 | 3,250 | 37 | 1,820 | 1.1 | 10.30% | 4.5 | 4.80% | 1:16 |
| MARCH | 13,550 | 3,400 | 39 | 1,860 | 1.1 | 10.20% | 4.5 | 4.70% | 1:15 |
| APRIL | 13,700 | 3,480 | 40 | 1,900 | 1.2 | 10.10% | 4.6 | 4.60% | 1:15 |
| MAY | 13,900 | 3,550 | 41 | 1,950 | 1.3 | 10.20% | 4.6 | 4.50% | 1:15 |
| JUNE | 14,100 | 3,600 | 42 | 2,000 | 1.3 | 10.40% | 4.6 | 4.60% | 1:15 |
| JULY | 14,800 | 4,150 | 67 | 1,620 | 2.6 | 12.10% | 3.9 | 7.20% | 1:19 |
| AUGUST | 15,200 | 4,300 | 70 | 1,580 | 2.8 | 12.40% | 3.8 | 7.50% | 1:19 |
| SEPTEMBER | 15,500 | 4,350 | 72 | 1,600 | 2.9 | 12.60% | 3.7 | 7.60% | 1:18 |
| OCTOBER | 15,800 | 4,400 | 74 | 1,650 | 3.0 | 12.80% | 3.7 | 7.70% | 1:18 |
| NOVEMBER | 16,000 | 4,500 | 75 | 1,700 | 3.1 | 13.00% | 3.6 | 7.80% | 1:18 |
| DECEMBER | 16,200 | 4,600 | 77 | 1,720 | 3.2 | 13.20% | 3.6 | 8.00% | 1:18 |
- Operational: Staff shortages, equipment downtime, EHR latency
- Seasonal: Heatwave + illness spike increased ER arrivals
- Administrative: Scheduling changes reduced elective throughput
- Systemic: Lack of dynamic resource planning and early alerts
- Staff shortage → longer triage → ↑ ER wait → ↓ satisfaction
- Imaging/lab delays → slower diagnosis → ↑ readmissions
- EHR issues → longer admin time → queue buildup
- Reduced elective slots → spillover into ER → system overload
- Staff rosters, sick leave, overtime logs
- Patient flow timestamps (arrival → discharge)
- Lab & imaging turnaround times
- Complaint categories and volumes
- Weather and illness incidence data
- EHR performance logs and error rates
- ER wait time ↑ 83% (42 → 77 min)
- Elective admissions ↓ 19% (2,000 → 1,620)
- Readmission rate ↑ 2.8 pp (10.4% → 13.2%)
- Satisfaction ↓ 1 full point (4.6 → 3.6)
- Estimated revenue loss from electives: $300–400K/year
- Add temporary staff (nurses + ER physicians)
- Open overflow beds and expedite equipment repairs
- Stabilize EHR system or rollback critical modules
- Improve patient communication (wait-time displays, discharge clarity)
- Fast-track minor ER cases (ESI 4–5)
- Reschedule electives to balance load
- Optimize lab/imaging throughput with extended hours
- Launch satisfaction recovery campaign
- Build real-time operations dashboard (staffing, wait times, complaints)
- Implement seasonal staffing models
- Invest in IT resilience and diagnostic capacity
- Create early-warning system for performance drops
The performance decline was driven by a triple convergence: internal resource gaps, seasonal demand surge, and system inefficiencies.
Recovery requires urgent operational fixes, tactical flow adjustments, and strategic resilience planning.
📈 With proper execution, 70–80% of lost performance can be recovered within 6–8 weeks.
In 2024, a mid-sized city with a population of 450,000 witnessed a 28% increase in theft and minor assault cases compared to 2023.
The goal: reduce these crimes by 40% within 12 months and improve police response efficiency.
- Crimes are concentrated in specific neighborhoods and nighttime hours.
- Police presence is low during peak crime periods.
- Urban planning gaps (poor lighting, inactive zones) contribute to vulnerability.
- Patrol distribution is static, leading to delayed response times.
- Citizen complaints and local app reports highlight blind spots in coverage.
Analyze spatial and temporal crime patterns, identify operational weaknesses, and propose innovative, data-driven interventions to reduce crime and improve public safety perception.
| Month | Total Crimes | Crime Rate per 1,000 Residents | % Nighttime Crimes | Instant Reports (<15 min) | Avg Response Time (min) | Active Hotspots | % Crimes in Poor Lighting Areas | Active Patrols | Functional Cameras | Citizen Reports | Safety Perception Index (1–5) |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Jan-23 | 210 | 0.47 | 42% | 95 | 17 | 6 | 38% | 120 | 85 | 22 | 4.2 |
| Feb-23 | 195 | 0.43 | 40% | 88 | 16 | 5 | 36% | 118 | 85 | 20 | 4.3 |
| Mar-23 | 205 | 0.46 | 41% | 90 | 16 | 6 | 37% | 119 | 86 | 21 | 4.3 |
| Apr-23 | 198 | 0.44 | 39% | 92 | 15 | 5 | 35% | 120 | 86 | 23 | 4.4 |
| May-23 | 202 | 0.45 | 40% | 94 | 15 | 6 | 36% | 121 | 87 | 24 | 4.4 |
| Jun-23 | 210 | 0.47 | 42% | 96 | 16 | 6 | 38% | 122 | 87 | 25 | 4.3 |
| Jul-23 | 215 | 0.48 | 43% | 97 | 16 | 6 | 39% | 122 | 88 | 26 | 4.2 |
| Aug-23 | 220 | 0.49 | 44% | 98 | 17 | 7 | 40% | 123 | 88 | 27 | 4.2 |
| Sep-23 | 225 | 0.50 | 45% | 99 | 17 | 7 | 41% | 123 | 88 | 28 | 4.1 |
| Oct-23 | 230 | 0.51 | 46% | 100 | 18 | 8 | 42% | 124 | 89 | 29 | 4.1 |
| Nov-23 | 235 | 0.52 | 47% | 101 | 18 | 8 | 43% | 124 | 89 | 30 | 4.0 |
| Dec-23 | 240 | 0.53 | 48% | 102 | 18 | 8 | 44% | 125 | 90 | 31 | 4.0 |
| Jan-24 | 260 | 0.58 | 52% | 105 | 19 | 9 | 46% | 115 | 90 | 35 | 3.9 |
| Feb-24 | 270 | 0.60 | 53% | 106 | 19 | 9 | 47% | 114 | 90 | 36 | 3.8 |
| Mar-24 | 280 | 0.62 | 54% | 107 | 20 | 10 | 48% | 113 | 91 | 37 | 3.8 |
| Apr-24 | 290 | 0.64 | 55% | 108 | 20 | 10 | 49% | 112 | 91 | 38 | 3.7 |
| May-24 | 295 | 0.65 | 56% | 109 | 20 | 11 | 50% | 110 | 91 | 39 | 3.7 |
| Jun-24 | 300 | 0.66 | 57% | 110 | 21 | 11 | 51% | 108 | 92 | 40 | 3.6 |
| Jul-24 | 310 | 0.69 | 58% | 111 | 21 | 12 | 52% | 107 | 92 | 41 | 3.6 |
| Aug-24 | 320 | 0.71 | 59% | 112 | 21 | 12 | 53% | 106 | 92 | 42 | 3.5 |
| Sep-24 | 330 | 0.73 | 60% | 113 | 22 | 13 | 54% | 105 | 93 | 43 | 3.5 |
| Oct-24 | 340 | 0.75 | 61% | 114 | 22 | 13 | 55% | 104 | 93 | 44 | 3.4 |
| Nov-24 | 345 | 0.76 | 62% | 115 | 22 | 14 | 56% | 103 | 93 | 45 | 3.4 |
| Dec-24 | 350 | 0.78 | 63% | 116 | 22 | 14 | 57% | 102 | 94 | 46 | 3.3 |
🎯 1. Crime Trend & Rate
This chart visualizes the monthly increase in total crimes alongside the crime rate per 1,000 residents. It highlights a sharp rise starting January 2024, marking a critical shift in public safety.
🌙 2. Nighttime vs Poor Lighting Crimes
This chart compares the percentage of crimes occurring at night with those in poorly lit areas. The parallel rise suggests a strong environmental correlation affecting safety.
🚓 3. Police Response Efficiency
This chart shows the inverse relationship between instant citizen reports and average police response time. Despite faster reporting, response delays increased, indicating operational strain.
🔥 4. Hotspots vs Patrols
This chart compares the number of active crime hotspots with police patrols. The growing gap reveals a mismatch between crime concentration and resource allocation.
📹 5. Technology & Citizen Engagement
This chart highlights the rise in functional surveillance cameras and citizen reports. It reflects growing public involvement and the role of technology in enhancing situational awareness.
🛡️ 6. Safety Perception vs Crime Rate
This chart shows the inverse correlation between crime rate and public safety perception. As crime increased, citizen confidence declined significantly.
- Operational: Static patrol scheduling, uneven resource allocation
- Environmental: Poor lighting, inactive commercial zones at night
- Technological: Limited camera coverage, slow response routing
- Social: Low citizen engagement, weak neighborhood watch systems
- Administrative: Lack of coordination between police, municipalities, and urban planners
- Poor lighting + closed shops → ↑ nighttime thefts
- Static patrols → delayed response → ↑ unresolved cases
- High hotspot density → resource strain → ↓ safety perception
- Citizen reports ↑ but response remains slow → trust erosion
- Camera coverage gaps → ↓ deterrence and evidence collection
- Geo-tagged crime reports with timestamps
- Patrol shift logs and GPS routes
- Lighting infrastructure maps and sensor data
- Public transport schedules and stop locations
- Business activity hours by zone
- Citizen complaint categories and resolution times
- Camera uptime logs and resolution quality
- Theft cases ↑ from 210/month to 350/month
- Crime rate ↑ from 0.47 to 0.78 per 1,000 residents
- Nighttime crimes ↑ from 42% to 63%
- Avg response time ↑ from 17 to 22 minutes
- Safety perception ↓ from 4.2 to 3.3
- Hotspots ↑ from 6 to 14 active zones
- Poor lighting crimes ↑ from 38% to 57%
- Deploy dynamic patrol routing based on live heatmaps
- Prioritize hotspot zones with increased nighttime coverage
- Repair and upgrade lighting in high-risk areas
- Launch public awareness campaign to boost app reporting
- Expand smart lighting with motion and activity sensors
- Pilot mobile police units in nightlife zones on weekends
- Integrate citizen app with reward system for useful reports
- Coordinate with urban planners to activate dead zones (e.g., night markets)
- Build real-time crime dashboard for city-wide monitoring
- Implement predictive patrol models using historical data
- Establish joint task force between police, municipalities, and transport authorities
- Launch “Eyes on the Street” initiative to promote active public spaces
The 2024 crime surge was driven by a convergence of spatial vulnerability, operational rigidity, and low civic engagement.
To reverse the trend, the city must adopt dynamic patrol strategies, smart infrastructure upgrades, and community-driven safety models.
📈 With full implementation, theft and minor assault cases can be reduced by up to 40% within 12 months, while restoring public trust and safety.
.....................................................................................................
In 2024, a regional area experienced a 45% surge in severe respiratory infections compared to seasonal averages.
The goal: reduce infection rates and hospital occupancy by 50% during peak season and ensure timely access to treatment for vulnerable populations.
- Delayed cluster detection due to weak early-warning systems.
- Uneven distribution of resources: some hospitals overcrowded, others underutilized.
- Low compliance with prevention measures in schools and markets.
- Limited mobility data to track social contact patterns.
- Vaccination coverage gaps among elderly and chronically ill groups.
Analyze outbreak dynamics, identify high-risk clusters, assess healthcare strain, and design innovative interventions to suppress transmission, balance hospital loads, and improve prevention compliance.
| Month | Daily Infection Rate per 100,000 | Hospital Occupancy (%) | ICU Bed Availability (%) | Avg ED Wait Time (min) | Pharmacy Anomaly Index | Detection Latency (hours) | Vaccination Coverage (Vulnerable) | Mobile Care Throughput | Smart Rerouting Success Rate (%) | PPE Package Coverage (%) | Citizen Report Resolution (≤48h) |
|---|---|---|---|---|---|---|---|---|---|---|---|
| JAN | 18.2 | 72% | 21% | 58 | 2.1 | 96 | 45% | 120 | 42% | 38% | 61% |
| FEB | 20.5 | 78% | 18% | 61 | 2.4 | 84 | 48% | 135 | 45% | 42% | 64% |
| MAR | 23.1 | 84% | 15% | 63 | 2.8 | 72 | 52% | 150 | 49% | 46% | 68% |
| APR | 25.7 | 88% | 13% | 65 | 3.2 | 60 | 56% | 165 | 52% | 50% | 71% |
| MAY | 27.4 | 92% | 11% | 67 | 3.6 | 54 | 59% | 180 | 56% | 54% | 74% |
| JUN | 26.8 | 89% | 14% | 64 | 3.3 | 48 | 62% | 195 | 60% | 58% | 76% |
| JUL | 24.5 | 83% | 17% | 60 | 2.9 | 42 | 65% | 210 | 64% | 62% | 78% |
| AUG | 21.7 | 76% | 20% | 56 | 2.5 | 36 | 68% | 225 | 68% | 66% | 80% |
| SEP | 18.9 | 68% | 24% | 52 | 2.2 | 30 | 71% | 240 | 72% | 70% | 82% |
| OCT | 15.4 | 61% | 28% | 48 | 1.8 | 24 | 73% | 255 | 76% | 74% | 84% |
| NOV | 12.7 | 58% | 32% | 45 | 1.5 | 18 | 74% | 270 | 80% | 78% | 86% |
| DEC | 10.3 | 54% | 36% | 42 | 1.2 | 12 | 75% | 285 | 84% | 82% | 88% |
This chart compares the Daily Infection Rate per 100,000 and Hospital Occupancy (%) across 2024.
Both indicators peaked in May (infection rate: 27.4, occupancy: 92%) and declined steadily to December (10.3 and 54%).
The chart shows a direct and proportional relationship, emphasizing how rising infections immediately impact hospital capacity.
This chart visualizes the inverse relationship between ED Wait Time and ICU Bed Availability.
As ICU availability dropped from 21% in January to 11% in May, ED wait time rose from 58 to 67 minutes.
The trend reversed in the second half of the year, confirming that critical care shortages lead to longer emergency delays.
This chart tracks the Pharmacy Anomaly Index and Detection Latency.
As pharmacy signals rose from 2.1 in January to 3.6 in May, detection latency dropped from 96 to 54 hours.
By December, latency reached 12 hours, showing a strong inverse relationship and validating pharmacy data as an early warning tool.
This chart shows the parallel growth of Vaccination Coverage and Mobile Care Throughput.
Coverage increased from 45% in January to 75% in December, while mobile care rose from 120 to 285 patients/day.
The trend reflects a positive correlation, highlighting the success of outreach efforts in reaching vulnerable populations.
This chart compares Smart Rerouting Success Rate and PPE Package Coverage.
Both metrics improved from 42% and 38% in January to 84% and 82% in December, showing a parallel upward trend.
The data reflects enhanced coordination in patient routing and preventive resource delivery.
This chart shows the percentage of Citizen Reports Resolved Within 48 Hours.
Resolution rates increased from 61% in January to 88% in December, indicating a steady improvement in system responsiveness.
The trend highlights the growing efficiency of civic feedback loops and public trust in outbreak management.
- Detection: Late cluster identification, fragmented reporting.
- Capacity: Static patient routing, bottlenecks at major hospitals.
- Access: Uneven vaccination and mobile care distribution.
- Behavior: Weak compliance in high-footfall areas.
- Data/Tech: Limited integration of pharmacy, mobility, and vaccination records.
- Pharmacy spikes → early outbreak signals → faster detection.
- High mobility + low prevention → rapid cluster growth.
- Hospital overload + weak rerouting → longer ED wait times.
- Low vaccination → higher severity and ICU demand.
- Rapid PPE distribution → improved compliance and reduced spread.
- Geo-tagged case reports with onset dates.
- Pharmacy dispensing logs with anomaly scores.
- Hospital occupancy and ICU bed availability in real time.
- Vaccination records by age and comorbidity.
- Mobility density indicators (markets, schools, transit).
- Citizen hotline/app complaint categories and resolution times.
- Cluster detection latency reduced from 7 days to 48 hours → ↓ spread by 46%.
- Hospital occupancy at peak reduced from 92% to 58% via smart rerouting.
- Vaccination coverage in vulnerable groups ↑ from 45% to 74%.
- Avg ED wait time ↓ from 65 to 45 minutes.
- PPE coverage ↑ to 80% of high-risk households within 48h.
- Activate pharmacy early-warning network.
- Unify case definitions and reporting cadence.
- Launch outbreak dashboard with live alerts.
- Distribute PPE kits to vulnerable households.
- Deploy mobile treatment and vaccination hubs.
- Implement smart patient routing platform.
- Run targeted prevention campaigns in schools and markets.
- Integrate pharmacy, mobility, and vaccination datasets.
- Build predictive cluster models.
- Balance hospital capacity with dynamic staffing and stock planning.
- Institutionalize outreach schedules for vulnerable zones.
- Establish cross-agency governance and quarterly drills.
The outbreak was fueled by late detection, uneven resource use, and weak prevention compliance.
By combining pharmacy-based early warning, mobile care, smart patient routing, PPE distribution, and targeted campaigns, the region can:
- Detect clusters within 48 hours.
- Reduce hospital occupancy by 34 percentage points.
- Increase vaccination coverage by nearly 30%.
- Restore public confidence and resilience in outbreak management.
In 2024, an urban region experienced unstable energy consumption patterns for the first nine months, followed by a severe surge in the last quarter (Oct–Dec).
The goal: reduce peak load by 25%, stabilize renewable integration, and mitigate rising household bills and emissions.
- Seasonal fluctuations: mild increases in winter (Jan–Feb), dips in spring, peaks in summer cooling.
- Winter collapse (Oct–Dec): sharp rise in consumption, outages, bills, and emissions.
- Renewable share dropped from 29% in September to 9% in December.
- Citizen complaints resolution weakened under system strain.
- Industrial demand remained a major driver of peak load.
Analyze consumption dynamics, identify seasonal risk factors, assess grid strain, and design interventions to:
- Balance loads across sectors.
- Increase renewable share.
- Reduce outages.
- Control household bills and emissions.
| Month | Residential (MWh) | Commercial (MWh) | Industrial (MWh) | Peak Load (%) | Renewable Share (%) | Outage Hours | Smart Meter Coverage (%) | Campaign Reach (%) | Complaints Resolved (%) | Avg Household Bill ($) | CO₂ Emissions (tons) |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Jan | 1250 | 980 | 1850 | 73% | 21% | 11 | 40% | 35% | 62% | 88 | 4300 |
| Feb | 1300 | 1020 | 1900 | 75% | 22% | 10 | 41% | 36% | 64% | 90 | 4400 |
| Mar | 1220 | 960 | 1820 | 71% | 23% | 9 | 42% | 38% | 66% | 85 | 4200 |
| Apr | 1280 | 1000 | 1880 | 74% | 24% | 8 | 43% | 40% | 68% | 87 | 4350 |
| May | 1400 | 1080 | 2000 | 77% | 25% | 9 | 44% | 42% | 70% | 95 | 4600 |
| Jun | 1350 | 1040 | 1950 | 75% | 26% | 8 | 45% | 44% | 72% | 92 | 4500 |
| Jul | 1450 | 1100 | 2050 | 78% | 27% | 7 | 46% | 46% | 74% | 98 | 4700 |
| Aug | 1380 | 1060 | 1980 | 76% | 28% | 7 | 47% | 48% | 76% | 94 | 4550 |
| Sep | 1500 | 1120 | 2100 | 79% | 29% | 6 | 48% | 50% | 78% | 100 | 4800 |
| Oct | 1800 | 1300 | 2350 | 87% | 18% | 15 | 49% | 52% | 70% | 125 | 5600 |
| Nov | 2000 | 1400 | 2500 | 91% | 12% | 20 | 50% | 54% | 68% | 150 | 6100 |
| Dec | 2200 | 1500 | 2650 | 94% | 9% | 25 | 51% | 56% | 66% | 180 | 6600 |
- Seasonality: Cooling in summer, heating in winter → unstable demand.
- Capacity: Industrial demand drives peak load.
- Renewables: Weak integration in winter months.
- Behavior: Limited campaign reach and weak compliance.
- Technology: Slow smart meter adoption.
- Environment: Rising CO₂ emissions linked to fossil fuel reliance.
- Residential + commercial demand → seasonal peaks.
- Industrial demand → grid overload.
- Renewable decline → outages increase.
- Smart meters + campaigns → compliance improvement.
- Household bills ↑ → emissions ↑ → public dissatisfaction.
- Appliance-level household consumption logs.
- Industrial load scheduling records.
- Renewable generation breakdown (solar, wind).
- Geo-tagged outage reports.
- Campaign effectiveness surveys.
- Citizen complaint categories and resolution times.
- Peak load surged from 79% in Sep → 94% in Dec.
- Renewable share dropped from 29% → 9%.
- Outage hours rose from 6 → 25 per month.
- Household bills increased from $100 → $180.
- CO₂ emissions escalated from 4800 → 6600 tons.
- Complaints resolved fell from 78% → 66%.
- Launch winter emergency awareness campaigns.
- Distribute energy-saving kits (insulation, efficient heaters).
- Activate real-time monitoring of peak loads.
- Expand smart meter deployment in high-demand districts.
- Reschedule industrial loads to off-peak hours.
- Integrate backup renewable storage (batteries).
- Build predictive seasonal demand models.
- Develop municipal partnerships for energy efficiency.
- Establish unified energy control center.
- Institutionalize winter preparedness drills.
The dataset reveals seasonal fluctuations followed by a severe winter crisis.
Key drivers: industrial demand, weak renewable integration, rising household bills, and growing emissions.
By combining smart meters, renewable storage, industrial rescheduling, and citizen engagement, the region can:
- Reduce peak load by 25%.
- Cut outages by 40%.
- Stabilize household bills.
- Lower emissions and restore public trust in energy management.