top of page
.png)
My Projects
Welcome to my portfolio. Here you’ll find a selection of my work. Explore my projects to learn more about my work. (Click icons for more projects)
IBM Cognos Analytic Sales & Service Dashboards
1.0. Executive Summary & Dashboard Overview
This review of the IBM Cognos, Analytics Sales Dashboard tracks enterprise-level financial and operational health, specifically focusing on profitability, inventory movement, model distribution, and dealer-level performance metrics.
Key Performance Indicators (KPIs) Summary
• Total Profit: $78,402,279.30: Shows strong overall business health and high-margin margins across the network.
• Total Quantity Sold: 58,118 units: Demonstrates solid aggregate product demand and sales volume.
• Average Quantity Sold: 19.373 units per transaction/record: Provides a baseline benchmark for standard order sizes or dealership batch outputs.
Deep-Dive Analytical Insights
1. Dealer Performance & Profit Concentration (Profit by Dealer ID)
• Observation: The bar chart tracking profitability by dealer ID reveals a tiered performance distribution.
• Insight: Dealer IDs such as 1288, 1301, and 1224 anchor the top end of the profitability spectrum, whereas lower-performing dealers with dealer IDs 1222, 1402 show a significant margin lag. The color-scaling feature indicates that profit concentration heavily favors the top 30% of dealers.
• Strategic Recommendation: Implement a best-practice sharing initiative. Analyze the operational strategies of top-tier dealers (like 1288) and apply those frameworks to underperforming dealers to lift the baseline.
2. Product Model Distribution (Quantity Sold by Model)
• Observation: The horizontal bar distribution displays volume concentration across various product models.
• Insight: Demand is heavily skewed toward mid-to-high-tier models, with certain SKUs (Stock Keeping Unit) significantly outperforming others in units moved.
• Strategic Recommendation: Optimize inventory management and supply chain allocation to ensure high-demand models never face stockouts, while reviewing low-volume models for potential markdown or phase-out.
Recommendations for Executive Leadership
1. Incentive Alignment: Restructure dealer bonus tiers around the performance metrics demonstrated by top dealers (1288 and 1301) to encourage higher-margin sales volumes.
2. Data Governance & Feature Expansion: Leverage the existing data module framework (incorporating MTD/YTD % changes, daily sales, and sentiment data visible on the left pane) to run predictive forecasting on customer sentiment versus dealer profitability.
2. Service Dashboard Overview
Building upon the sales performance review, this analysis shifts focus to the IBM Cognos Analytics Service & Quality Dashboard. This view monitors post-sale metrics, product reliability, customer sentiment, and warranty/recall patterns across models.
Key Operational Metrics & Visual Breakdown
• Top-Left (# of Recalls by Model): Displays recall distribution across models named Beaufort, Champlain, Hudson, Labrador, and Salish. The Beaufort model exhibits the highest recall volume, closely followed by the Labrador.
• Top-Right (Sentiment Analysis): A treemap visualizing customer feedback distribution broken down into Positive, Neutral, and Negative sentiments. The dominant blocks indicate that a significant share of customer feedback falls under Neutral and Positive categories, though localized negative sentiment requires mitigation.
• Bottom-Left (Profit and Quantity Sold for Month): A dual-metric tracking chart showing monthly volume (purple bars) alongside profit trends (blue line) across the calendar year. It highlights an efficiency dip around August/September before recovering toward year-end.
• Bottom-Right (# of Recalls by Model and Affected System): A matrix heatmap correlating models with vehicle systems (such as Brakes, Engine, Electrical, Fuel Supply, Steering, Suspension, Structure, and Tires). Notably, the interactive hover tooltip highlights Beaufort | Engine with 30,884 recalls, pointing to a specific mechanical vulnerability.
Deep-Dive Analytical Insights
1. Product Reliability Hotspots:
o The matrix heatmap pinpoints mechanical failure clusters. The high concentration of engine-related recalls in models like the Beaufort indicates a pressing need for supplier quality audits or engineering design reviews.
2. Sentiment vs. Quality Correlation:
o While overall customer sentiment remains stable, clusters of negative feedback directly correspond with months and models experiencing higher recall frequency. Resolving underlying hardware flaws will directly improve brand sentiment.
3. Seasonal Profit & Volume Alignment:
o The monthly sales/profit trend reveals stable volume conversion, but margin compression during mid-year months suggests potential warranty service cost spikes or promotional discounting that diluted profitability.
Strategic Recommendations for Executive Leadership
• Targeted Quality Control: Prioritize engineering interventions on high-recall modules (e.g., the Beaufort engine systems) to dramatically cut warranty servicing costs.
• Customer Success Loop: Integrate the sentiment tracking data with the service logs to proactively reach out to customers associated with negative sentiment nodes, turning potential churn into retention.
• Cross-Functional Data Synergy: Combine these service-side metrics with the previous sales dashboards to evaluate the net lifetime profit of models after factoring in recall and warranty repair overhead.
This review of the IBM Cognos, Analytics Sales Dashboard tracks enterprise-level financial and operational health, specifically focusing on profitability, inventory movement, model distribution, and dealer-level performance metrics.
Key Performance Indicators (KPIs) Summary
• Total Profit: $78,402,279.30: Shows strong overall business health and high-margin margins across the network.
• Total Quantity Sold: 58,118 units: Demonstrates solid aggregate product demand and sales volume.
• Average Quantity Sold: 19.373 units per transaction/record: Provides a baseline benchmark for standard order sizes or dealership batch outputs.
Deep-Dive Analytical Insights
1. Dealer Performance & Profit Concentration (Profit by Dealer ID)
• Observation: The bar chart tracking profitability by dealer ID reveals a tiered performance distribution.
• Insight: Dealer IDs such as 1288, 1301, and 1224 anchor the top end of the profitability spectrum, whereas lower-performing dealers with dealer IDs 1222, 1402 show a significant margin lag. The color-scaling feature indicates that profit concentration heavily favors the top 30% of dealers.
• Strategic Recommendation: Implement a best-practice sharing initiative. Analyze the operational strategies of top-tier dealers (like 1288) and apply those frameworks to underperforming dealers to lift the baseline.
2. Product Model Distribution (Quantity Sold by Model)
• Observation: The horizontal bar distribution displays volume concentration across various product models.
• Insight: Demand is heavily skewed toward mid-to-high-tier models, with certain SKUs (Stock Keeping Unit) significantly outperforming others in units moved.
• Strategic Recommendation: Optimize inventory management and supply chain allocation to ensure high-demand models never face stockouts, while reviewing low-volume models for potential markdown or phase-out.
Recommendations for Executive Leadership
1. Incentive Alignment: Restructure dealer bonus tiers around the performance metrics demonstrated by top dealers (1288 and 1301) to encourage higher-margin sales volumes.
2. Data Governance & Feature Expansion: Leverage the existing data module framework (incorporating MTD/YTD % changes, daily sales, and sentiment data visible on the left pane) to run predictive forecasting on customer sentiment versus dealer profitability.
2. Service Dashboard Overview
Building upon the sales performance review, this analysis shifts focus to the IBM Cognos Analytics Service & Quality Dashboard. This view monitors post-sale metrics, product reliability, customer sentiment, and warranty/recall patterns across models.
Key Operational Metrics & Visual Breakdown
• Top-Left (# of Recalls by Model): Displays recall distribution across models named Beaufort, Champlain, Hudson, Labrador, and Salish. The Beaufort model exhibits the highest recall volume, closely followed by the Labrador.
• Top-Right (Sentiment Analysis): A treemap visualizing customer feedback distribution broken down into Positive, Neutral, and Negative sentiments. The dominant blocks indicate that a significant share of customer feedback falls under Neutral and Positive categories, though localized negative sentiment requires mitigation.
• Bottom-Left (Profit and Quantity Sold for Month): A dual-metric tracking chart showing monthly volume (purple bars) alongside profit trends (blue line) across the calendar year. It highlights an efficiency dip around August/September before recovering toward year-end.
• Bottom-Right (# of Recalls by Model and Affected System): A matrix heatmap correlating models with vehicle systems (such as Brakes, Engine, Electrical, Fuel Supply, Steering, Suspension, Structure, and Tires). Notably, the interactive hover tooltip highlights Beaufort | Engine with 30,884 recalls, pointing to a specific mechanical vulnerability.
Deep-Dive Analytical Insights
1. Product Reliability Hotspots:
o The matrix heatmap pinpoints mechanical failure clusters. The high concentration of engine-related recalls in models like the Beaufort indicates a pressing need for supplier quality audits or engineering design reviews.
2. Sentiment vs. Quality Correlation:
o While overall customer sentiment remains stable, clusters of negative feedback directly correspond with months and models experiencing higher recall frequency. Resolving underlying hardware flaws will directly improve brand sentiment.
3. Seasonal Profit & Volume Alignment:
o The monthly sales/profit trend reveals stable volume conversion, but margin compression during mid-year months suggests potential warranty service cost spikes or promotional discounting that diluted profitability.
Strategic Recommendations for Executive Leadership
• Targeted Quality Control: Prioritize engineering interventions on high-recall modules (e.g., the Beaufort engine systems) to dramatically cut warranty servicing costs.
• Customer Success Loop: Integrate the sentiment tracking data with the service logs to proactively reach out to customers associated with negative sentiment nodes, turning potential churn into retention.
• Cross-Functional Data Synergy: Combine these service-side metrics with the previous sales dashboards to evaluate the net lifetime profit of models after factoring in recall and warranty repair overhead.
Micro Gas Turbine Electrical Energy Prediction
In this project, I applied regression models to predict the electrical power output of a 3-kilowatt micro gas turbine based on its input control signal over time.
The dataset included over 71,000 time-series measurements, capturing both smooth changes and sudden transitions where the turbine’s output lagged behind the input.
Using regression allowed me to model not just the steady-state relationships, but also the more challenging transitional behaviors where delays made the prediction task less straightforward.
I was motivated by how regression models can go beyond simple curve fitting to capture real-world engineering systems. Since micro turbines play a role in distributed and sustainable energy, being able to accurately forecast their performance with data-driven methods has practical value for improving efficiency, reliability, and energy planning.
The dataset included over 71,000 time-series measurements, capturing both smooth changes and sudden transitions where the turbine’s output lagged behind the input.
Using regression allowed me to model not just the steady-state relationships, but also the more challenging transitional behaviors where delays made the prediction task less straightforward.
I was motivated by how regression models can go beyond simple curve fitting to capture real-world engineering systems. Since micro turbines play a role in distributed and sustainable energy, being able to accurately forecast their performance with data-driven methods has practical value for improving efficiency, reliability, and energy planning.
Operation Defend the North Vancouver 2025: White Paper
A fictitious company ODTN Telecoms, recently executed a swift and coordinated incident response operation following a targeted cyber-attack on its internal network.
The breach was first detected through abnormal login activity and unauthorized access attempts. The security team immediately activated the incident response plan, isolating affected systems to prevent lateral movement. Forensic analysis confirmed the presence of malware designed to exfiltrate customer data.
Containment procedures included network segmentation and credential resets. The team collaborated with external cybersecurity experts to assess the scope and neutralize the threat.
Communication protocols ensured stakeholders and regulators were informed in real-time. Within 48 hours, systems were restored with enhanced monitoring in place.
A full post-incident review identified gaps and recommended policy updates. ODTN reaffirmed its commitment to data security and operational resilience.
The breach was first detected through abnormal login activity and unauthorized access attempts. The security team immediately activated the incident response plan, isolating affected systems to prevent lateral movement. Forensic analysis confirmed the presence of malware designed to exfiltrate customer data.
Containment procedures included network segmentation and credential resets. The team collaborated with external cybersecurity experts to assess the scope and neutralize the threat.
Communication protocols ensured stakeholders and regulators were informed in real-time. Within 48 hours, systems were restored with enhanced monitoring in place.
A full post-incident review identified gaps and recommended policy updates. ODTN reaffirmed its commitment to data security and operational resilience.
.jpeg){kind=small}
bottom of page