About

Starting Semester: Fall 2026
Assigned: No
Location: Alpharetta

Lending Science DM, Inc

Client Profile

Lending Science DM Inc is a data driven marketing and analytics company that helps organizations in financial and insurance services identify, target, and acquire customers through optimized omnichannel campaigns. Its operating environment combines consumer credit, demographic, behavioral, and campaign performance data with audience selection rules, segmentation, suppression requirements, quality controls, production activities, and performance measurement. The company seeks a scalable operating model that supports growth without sacrificing quality, control, or campaign performance.

Project Description

Background: Campaign volume and complexity have increased, while critical activities continue to depend on manual review, data preparation, quality control, exception handling, and coordination across systems and stakeholders. These dependencies can extend turnaround time, create rework, consume analytical capacity, and constrain scalability.

Opportunity: Team will analyze, model, and redesign the end-to-end campaign selection and production system. Artificial intelligence, machine learning, and automation may be incorporated when justified, but they will serve as enabling components within an integrated engineering design rather than as the project's primary academic focus.

Desired Outcome: A more efficient, controlled, and scalable operating system that reduces cycle time and manual effort while maintaining or improving quality, throughput, campaign performance, operational risk management, and economic value.

Scope
Design: Map and quantify the current system; define engineering requirements and baseline measures; identify flow, capacity, quality, and resource constraints; develop at least three integrated alternatives; evaluate them through optimization, simulation, statistics, experimental design, or structured decision analysis; and deliver a sponsor approved future state design, build backlog, acceptance criteria, and pilot plan.

Execution and Build: Convert the approved design into detailed specifications; build and integrate the priority workflow, analytical, automation, quality control, dashboard, or decision support components; complete system and user testing; execute a controlled pilot; measure results against baseline and design predictions; refine the solution; and prepare it for implementation and operational handoff.

Primary Deliverable: A validated future state campaign selection and production system, supported by a quantitative evaluation model and implemented through a functional, tested solution. The final package will include measured pilot results, process and control documentation, operating procedures, monitoring measures, economic analysis, implementation requirements, and a deployment readiness roadmap. If production deployment is outside the student team's access or authority, the team will provide a sponsor accepted pilot and implementation ready artifacts.

Skills

• Python
• SQL
• Tableau or PowerBI
• Machine Learning
• AI /Predictive Analytics
• Statistical analysis and experimental design
• Decision and economic analysis
• Model validation and sensitivity analysis
• Systems and process engineering
• Value stream and data flow mapping
• Operations research and optimization
• Discrete event simulation
• Capacity queueing and resource analysis
• Quality engineering and control design
• Requirements definition
• Strong Presentation Skills
• Project and stakeholder management
• Human centered work design
• Technical documentation and presentation
• Data privacy and responsible AI
• Financial services or business/marketing analytics interest

Data Access Requirement