Mrugesh D. Kharwar
Business Analyst & Operations Manager, Jala Bapa Hospitality LLC
El Monte, California, United States
Actions
Mrugesh Kharwar is a Business Analyst and Operations Manager at Jala Bapa Hospitality LLC, where he leads day-to-day operations and data strategy for Aqua Inn Hotel and other properties under the same ownership in Los Angeles. He combines hands-on hotel management with analytics—building Power BI dashboards, modeling occupancy and revenue trends, and translating PMS, OTA, and financial data into decisions independent operators can actually act on. His work focuses on the practical side of hospitality intelligence: clean data pipelines, reliable KPIs (ADR, RevPAR, GOP), competitive rate positioning, and guest sentiment analysis across Booking.com, Expedia, and TripAdvisor.
Before moving into hospitality, Mrugesh spent over a decade in enterprise data and risk analytics — most recently as a Risk Assessment Analyst at Delta Dental of California, supporting their Enterprise Risk Management and GRC programs. He holds an MBA in Business Statistics & Data Analytics from Westcliff University and is currently pursuing a Doctorate in Business Intelligence & Data Analytics at the same institution. He speaks and writes on dashboard reliability, data trust, and bringing enterprise-grade analytics discipline to independent hotels and motels.
Links
Area of Expertise
Topics
Turning Risk Registers into Early Warning Systems with Power BI Dashboards
Most operational risk still lives in static registers and monthly reports that describe what already went wrong. By the time a problem shows up in a report, the moment to act has usually passed. This session shows how to close that gap by turning a Power BI environment into a live early warning layer for operational and enterprise risk, rather than a set of dashboards that only look backward.
I will walk through a working monitoring system that I designed and deployed in a live operational setting. Using Power BI and business intelligence dashboards, it brings together operational, booking, and financial data, scores emerging risk on occupancy and cancellation signals, and puts those signals in front of a non technical team in a form they can act on within hours rather than days. The whole approach is built from tools that a Power BI practitioner already has, so the focus stays on the data model and the method rather than on any extra platform or spend.
Attendees will leave with a concrete, adaptable framework. I will cover how to structure a risk register so it feeds a live monitoring layer, how to design composite risk scores from operational data, how to shape the report so response time actually improves, and how to validate a predictive model before you trust it in production. I will share the real results from the deployment, including a 14.3% reduction in undetected risk events, a response time improved from 4.7 hours to 1.8 hours, and predictive model performance scores of 0.89 and 0.93. The underlying framework was published as a peer reviewed paper in the American Journal of Technology in 2026.
What makes this different is the reframe. Predictive analytics here is not forecasting for its own sake. It is an early warning capability, a way to shorten the distance between a signal appearing in the data and a person deciding to act on it. That idea travels well beyond hospitality, to anyone using Power BI to keep an operation steady under pressure.
I would enjoy sharing this with the Power BI User Group Italy community. It is a practical, first hand account of building something that works with the tools people in this group use every day, and I would value the exchange with an audience that lives in this space.
Intelligence Dashboards for Operational and Enterprise Risk Monitoring
Most operational risk still lives in static registers and monthly reports that describe what already went wrong. By the time a problem surfaces, the window to act has usually closed. This session shows how to turn that reactive posture into a proactive one by treating risk monitoring as a real time data problem rather than a documentation exercise.
I will walk through a working early warning system that I designed and deployed in a live operational setting. It ingests operational, booking, and financial data, scores emerging risk from occupancy and cancellation signals, and surfaces those signals on business intelligence dashboards that a non technical team can act on within hours rather than days. The system is deliberately built from tools most teams already have, so the focus stays on the method and the data model rather than on any single vendor or platform.
Attendees will leave with a concrete, adaptable framework. I will cover how to structure a risk register so it feeds a live monitoring layer, how to design composite risk scores from operational data, how to measure and shorten response latency, and how to validate predictive models before trusting them in production. I will share the real numbers from the deployment, including a 14.3% reduction in undetected risk events, a response time improved from 4.7 hours to 1.8 hours, and predictive models validated at an area under the receiver operating characteristic curve, or AUC-ROC, of 0.89 for occupancy risk and 0.93 for cancellation risk. The underlying framework was published as a peer reviewed paper in the American Journal of Technology in 2026.
What makes this different is the reframe. Predictive analytics here is not about forecasting for its own sake. It is an early warning capability, a way to compress the gap between a signal appearing in the data and a human deciding to act on it. That framing matters to anyone responsible for keeping a data intensive operation reliable under pressure, from analysts and engineers to the operations leaders who depend on their signals.
This is a first hand account, not a product pitch. I would value the chance to share what worked, what did not, and what I would design differently for teams operating at much larger scale.
Mrugesh D. Kharwar
Business Analyst & Operations Manager, Jala Bapa Hospitality LLC
El Monte, California, United States
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top