Desafio BAT Brasil:
BAT – Smart Replacement Matrix: Predictive Fleet Renewal

Início 16/07/2025
| Fim 06/08/2025

descrição

CHALLENGE
Today, vehicle replacement is managed through a fixed 3-year cycle, regardless of actual usage or condition. This one-size-fits-all approach leads to inefficiencies: some vehicles are replaced too early, increasing costs unnecessarily, while others are kept too long, increasing maintenance risks and lowering user satisfaction. BAT seeks a smarter, data-driven way to define the optimal replacement timing for each vehicle.

COUNTRY
Brazil, with potential expansion to other Latam South countries.

PAIN POINT
Fixed renewal cycles do not reflect vehicle condition or usage

Premature replacements increase CAPEX

Overdue replacements lead to breakdowns and higher OPEX

Lack of predictability in planning and budgeting

KEY CRITERIA
Predictive analytics using real-world data (mileage, repairs, downtime, etc.)

Integration with existing fleet systems (data already available)

Customizable rules, thresholds, and logic

Visual dashboards or BI tools for fleet monitoring

Alerts and proactive recommendations for replacement timing

Scalable solution adaptable to multiple vehicle types and locations

Capacity to incorporate new data sources over time

Clear cost-optimization potential

EXPECTED OUTCOMES
Optimized replacement timing per vehicle

Reduced unnecessary replacements and related costs

Fewer maintenance incidents and breakdowns

More accurate and proactive fleet renewal planning

Greater transparency and data-driven decisions

Increased vehicle availability and driver satisfaction

BUSINESS CONTEXT & OBJECTIVES
The Procurement and Fleet teams aim to modernize BAT’s approach to fleet renewal. The current 3-year renewal policy lacks alignment with actual vehicle performance and usage data. BAT is looking for a predictive, potentially AI-based solution that leverages existing data (e.g., km driven, repair history) to recommend the best replacement timing per unit. This would allow smarter planning, reduced total cost of ownership, and improved user experience.

TARGET AUDIENCE
Procurement, Facilities, Fleet, Logistics, and Operations teams

LOCATION
Brazil, with initial focus on São Paulo, Rio de Janeiro, and Uberlândia

KPIs
% of replacements optimized vs. fixed cycle

Cost savings from early/late replacements

Decrease in unplanned maintenance or downtime

User satisfaction with vehicle condition

Adoption rate and usability of the solution/platform

Accuracy of forecasts over time

TIMELINE
Solution scouting & analysis: Q3 2025

Proof of concept / pilots: Q1 2026

Expansion / implementation: Q2 2026

FINAL THOUGHTS
We are looking for innovative, data-driven solutions that allow us to predict the ideal replacement time for each vehicle based on its lifecycle and performance. The goal is to increase planning precision, reduce inefficiencies, and deliver long-term cost savings through smarter, evidence-based fleet renewal decisions.