Lead Data Scientist

Caterpillar Inc.•Peoria, IL

1d•Onsite

About The Position

When you join Caterpillar, you're joining a global team who cares not just about the work we do – but also about each other. We are the makers, problem solvers, and future world builders who are creating stronger, more sustainable communities. We don't just talk about progress and innovation here – we make it happen, with our customers, where we work and live. Together, we are building a better world, so we can all enjoy living in it. As a Lead Data Scientist in Corporate Aftermarket Finance Services, you will provide specialized data science expertise and technical leadership to support all aspects of forecast analytics for Caterpillar aftermarket parts and related special projects. The role is responsible for managing and optimizing key analytical processes that support the enterprise-critical Dealer Parts Orders (DPO) forecast and insights generation. This position oversees the end‑to‑end Parts Long‑Term Forecast (LTF) process – spanning system architecture design and implementation; data engineering and statistical model development; user training, and stakeholder approvals – to ensure accurate and efficient forecasting. The role owns design, maintenance and enhancements of Power BI dashboards to deliver clear, actionable insights to stakeholders. A core responsibility is safeguarding the integrity of both the Sales & Operations Planning (S&OP) forecast disaggregation and the annual business plan disaggregation for DPO. This includes owning the statistical modeling required to calculate probabilistic confidence intervals for aftermarket parts forecasts. The position also ensures timely, accurate updates to DPO systems and provides expert-level support for all product‑based allocation inquiries. The role requires strong planning and prioritization skills to independently complete broadly scoped assignments and drive key business outcomes. Success in this position directly contributes to organizational goals related to customer satisfaction, process quality, accuracy, efficiency, and continuous improvement.

Requirements

Business Statistics: In-depth knowledge of statistical methods, models, tools, and techniques, as used as industry-best-practices to solve diverse business problems and support business decision-making.
Time Series Modeling: In-depth knowledge of fundamental concepts of time series stationarity, seasonality, and time series decomposition. Extensive experience in applying statistical tools and techniques for time series analysis and modelling.
Machine Learning: In-depth knowledge of principles, technologies and algorithms of machine learning and deep learning; Demonstrated ability to develop, implement and deliver related systems, products and services.
Accuracy and Attention to Detail: Understanding the necessity and value of accuracy; ability to complete tasks with high levels of precision.
Analytical Thinking: Knowledge of techniques and tools that promote effective analysis; ability to determine the root cause of organizational problems and create alternative solutions that resolve these problems.
Platform and Programming Skill: Knowledge of basic concepts and capabilities of analytics programming languages; Ability to use tools, techniques and platforms in order to write and modify analytics programs; Proficiency in the following: Analytics Programming Language: Python, R, SQL and SAS Data Engineering and Warehousing: Snowflake ML Platform: PyTorch or Tensorflow Insights Delivery: PowerBI; Rshiny / Dash / Streamlit Cloud Platform: AWS (S3, EC2, LAMBDA, Glue, Sagemaker) or its equivalent in Azure AI and Gen AI Orchestration: Ollama, AWS Bedrock / Sagemaker or Azure ML / Azure OpenAI Query and Database Access Tools: Knowledge of data management systems; ability to use, support and access facilities for searching, extracting and formatting data for further use; Specifically, Proficiency in Snowflake SQL.
Requirements Analysis: Knowledge of tools, methods, and techniques of requirement analysis; ability to elicit, analyze and record required business functionality and non-functionality requirements to ensure the success of a system or software development project. Specifically, Experience in Azure DevOps

Nice To Haves

Doctoral or Master’s degree with 5 years of experience or a Bachelor’s degree with 10 years of experience in Computer Science, Mathematics, Engineering, Accounting, Statistics, Data Science, Business Analytics, or a closely related field with extensive coursework in mathematical and statistical modeling.
5+ years of extensive experience in applying statistical models and methods to solve wide range of industry problems.
5+ years of extensive experience in applying statistical tools and techniques for time series analysis and modelling; demonstrating deep understanding of fundamental concepts of time series analysis: stationarity; seasonality; time series decomposition.
5+ years of extensive experience in developing end-to-end analytics solutions that span from data pipeline to insights delivery.
Deep expertise and experience in applying classical statistical modelling methods, tools and techniques for time series forecasting included in the GLM, ARIMA and State Space family of models.
Deep expertise and experience in contemporary deep learning tools and techniques for time series forecasting included in Transformer family of models with self-attention mechanism.
Deep understanding of models and methods for Hierarchical time series and forecast reconciliation.
Extensive experience and proficiency in R, Python and SQL / Snowflake queries
Experience with AWS Cloud platform and AWS Glue
Experience with Alteryx and SAS
Extensive experience with PowerBI for development of reporting dashboards
Experience with Rshiny / Dash / Streamlit for development of interactive web application for forecast analytics.
High level of interpersonal skills and excellent communication and storytelling skills
Experience in Value Stream Mapping for Business Process analysis and improvement

Responsibilities

Responsible for answering questions regarding the Dealer Parts Orders (DPO) product-based allocation.
Own the Parts LTF process: system architecture design, analytics solution development, and user training.
Own the design, development and maintenance of PowerBI dashboards to deliver the forecast analytics solutions.
Responsible for the integrity of the disaggregation of the S&OP forecast.
Own the foundational research in leveraging Gen AI LLM models for explainable forecast initiative.
Lead design and implementation of LLM-powered analytics insight generation to explain forecast miss
Own the statistical modelling for calculating forecast confidence intervals for aftermarket parts.
Responsible for the integrity of the annual business plan disaggregation for DPO.
Regularly and accurately maintain and update DPO systems and answer all related queries for their assigned allocations.
Responsible for setting priorities and preparing work plan to complete broadly defined assignments and achieve desired results.
Responsible for Value Stream Mapping for Business Process analysis and improvement.
Responsible for Impact key quality goals including Customer Satisfaction, Continuous Improvement, Timeliness, Accuracy, Efficiency, Cost Savings, Process Quality, etc.