Skip to content
View SEANSKIDATA's full-sized avatar

Block or report SEANSKIDATA

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SEANSKIDATA/README.md

Sean Codner

Enterprise Operations Analytics | Workforce Planning | Capacity Optimization | Decision Support | SQL • Python • Tableau

📍 Houston, Texas 🔗 LinkedIn


The Way I Think About Data

Most analytics projects explain what happened.

Mine are designed to answer a different question:

What should we do next?

My career has been built inside operations—ATM network management, workforce planning, contact centers, and high-volume service environments where decisions affect customers, service levels, and revenue in real time.

That background shapes every project I build.

I don't view analytics as reporting.

I view analytics as decision support.

A low-volume casino ATM located 142 miles from the nearest branch with only 0.8 days of cash remaining is operationally more critical than a high-volume urban ATM with six days of runway.

Traditional reporting treats them differently.

Operational analytics should not.


Enterprise Portfolio

4 Enterprise Analytics Projects

2 Operational Domains

18+ Years of Enterprise Operations Experience

Specializing in transforming operational data into actionable business decisions.


Technical Skills

Analytics & Engineering

  • SQL
  • Python
  • Pandas
  • NumPy
  • Matplotlib
  • Tableau
  • Business Intelligence

Domain Expertise

  • Workforce Management
  • Workforce Capacity Planning
  • Intraday Staffing
  • Erlang C Modeling
  • Shrinkage Planning
  • Service Level Management
  • Call Center Forecasting
  • ATM Network Operations
  • Cash Management Analytics
  • Operational Risk Intelligence
  • Executive Decision Support

Portfolio

Two parallel tracks.

One philosophy.

Operational analytics creates the greatest value when it moves beyond describing operations and begins improving operational decisions.


📋 Track 1 — Enterprise Workforce Planning & Optimization

🏗️ Enterprise Workforce Planning & Optimization Engine (Active Development)

→ View Repository

Tools

Python • Pandas • NumPy • Matplotlib • Erlang C • Jupyter Notebook

Business Question

Given real contact-center arrival data, can we build an enterprise workforce planning workflow—from interval-level forecasting through staffing recommendations that leadership can act upon?

The most valuable insight wasn't the forecast itself.

It was what happened after the forecast.


Current Development Status

Module Description Status
Forecast Engine Interval-level forecasting with holdout validation (21.2% WAPE)
Capacity Planning Erlang C staffing, shrinkage modeling, FTE sizing
Staffing Gap Analysis Required vs. scheduled staffing by interval
Workforce Optimization Engine Staffing redistribution without additional hiring
Decision Lab Scenario simulator for staffing decisions
Multichannel Planning Voice, Chat, Email planning methodologies
Executive Dashboard Leadership KPI dashboard 🔄
Executive Brief Executive summary and recommendations 🔄

Validated Findings

Metric Result
Forecast Accuracy 21.2% WAPE
Staffing Variance -1.6%
Understaffed Intervals 53%
Overstaffed Intervals 44%
Balanced Intervals 3%
Delivered Service Level 62.4%
Target Service Level 80%

These findings were independently validated to ensure that every business conclusion accurately reflects the underlying calculations.

Key Insight

Total scheduled staffing was within 1.6% of calculated requirements.

Yet:

  • 53% of operating intervals were understaffed.
  • 44% were overstaffed.
  • Service level achieved only 62.4% against an 80% target.

The issue wasn't total staffing.

It was interval-level workforce distribution.


Workforce Optimization

Redistributing existing staffing—without adding a single FTE—recovered approximately 20 percentage points of service level and exceeded the 80% target.

The project demonstrates how workforce analytics can improve operational performance before recommending additional hiring.


Decision Lab

Scenario Projected Service Level 80% Target
Current Schedule 62.4%
Redistribute Existing Staff 82.5%
Add Five FTE 95.5%
Reduce AHT 15% 76.2%
Reduce Shrinkage 4 Points 69.3%
Combined Improvements 94.4%

Peer-reviewed by an experienced Workforce Management practitioner (Encore Capital Group, 13+ years).


📊 Track 2 — Enterprise ATM Operations Analytics

Three projects.

One operational argument.

Transaction volume alone is an incomplete measure of operational risk.


🏧 ATM Predictive Demand Model

→ View Repository | → Live Tableau Dashboard

Predictive cash forecasting designed to identify which ATMs will become operationally critical within the next 72 hours—and recommend proactive replenishment priorities.

Highlights

  • Revenue at Risk: $830,880
  • Critical Locations: 5
  • Immediate Dispatches: 5
  • Average Time to Failure: 0.6 Days

One of the project's signature concepts is the Refund Rush Effect—a real operational scenario demonstrating how external business changes can invalidate historical demand assumptions almost overnight.


🔍 ATM Network Risk Intelligence

Composite operational risk scoring framework combining:

  • Cash Position
  • Distance
  • Location Type
  • Revenue Impact
  • Operational Criticality

into a single enterprise prioritization model.


📊 ATM Network Analysis Version 2

Foundational SQL analytics demonstrating why transaction volume alone is an incomplete measure of ATM operational priority.


Portfolio Progression

Project Focus Primary Tools Status
ATM Network Analysis V2 ATM Analytics SQL
ATM Network Risk Intelligence Risk Intelligence SQL
ATM Predictive Demand Model Predictive Analytics Python • SQL • Tableau
Enterprise Workforce Planning & Optimization Engine Workforce Planning Python • Erlang C 🚧

Professional Background

Workforce Management

MCI Telecommunications

Intraday Workforce Management for a 350+ agent multi-site contact center.

Experience includes:

  • Intraday staffing
  • Abandonment-rate management
  • Schedule exception coding
  • IEX TotalView
  • Workforce coordination across multiple time zones

Enterprise ATM Operations

Cardtronics / NCR

Supported one of North America's largest ATM networks.

Experience includes:

  • 45,000+ ATM terminals
  • 98% contractual uptime SLA
  • ~$8M annual theft-loss avoidance coordination
  • Executive operational reporting
  • Enterprise cash logistics

Fintech Operations

Margo / PowerCoin

Built cash operations from the ground up for an early-stage Bitcoin ATM operator.


Current

Independent Operations Analytics Consultant focused on enterprise workforce planning, operational analytics, forecasting, and decision support.


Let's Connect

I'm interested in remote opportunities involving:

  • Workforce Planning
  • Capacity Planning
  • Operations Analytics
  • Business Intelligence
  • Data Analytics
  • Fintech
  • HealthTech
  • SaaS
  • Payments

particularly where analytics directly support operational decision-making.

🔗 LinkedIn — Sean Codner


Portfolio datasets are either real (Technion "Anonymous Bank" call-center data) or synthetic datasets designed to model realistic enterprise operating environments. All synthetic workforce assumptions are explicitly identified throughout the projects.

Pinned Loading

  1. ATM-Predictive-Demand-Model ATM-Predictive-Demand-Model Public

    72-hour ATM cash demand forecasting model Python, SQL window functions, Tableau

    Jupyter Notebook

  2. ATM-Network-Risk-Intelligence ATM-Network-Risk-Intelligence Public

    ATM network cash risk framework that moves beyond volume reporting — modeling terminal criticality, cluster exposure, and bank-branded reputational risk using distance, cash tolerance, and forward-…

  3. ATM-Network-Analysis-Version-2 ATM-Network-Analysis-Version-2 Public

    ATM network cash demand and withdrawal performance analysis using SQL and dashboard visualization.