Data Scientist - Metro Transit

Who We Are

Metro Transit (www.metrotransit.org) is the largest provider of transit service in the Twin Cities of Minneapolis and St. Paul, Minnesota, and the surrounding seven-county metropolitan area. The agency operates bus and rail service essential to the region’s mobility, and also provides resources for carpooling, van pooling and bike commuting. Metro Transit helps people get to where they’re going, reduces regional traffic congestion and promotes a cleaner environment. Metro Transit is a division of the Metropolitan Council.

The Metropolitan Council is the regional government for the seven-county Twin Cities metropolitan area. We plan 30 years ahead for the future of the metropolitan area and provide regional transportation, wastewater, and housing services. More information about us on our website.

We are committed to supporting a diverse workforce that reflects the communities we serve.

The Analytics & Research Group within the Strategic Initiatives Department of Metro Transit acts to support all functional areas of Metro Transit through data extraction, manipulation, analysis, visualization, and statistical synthesis. We develop original research projects using transit data, and apply the latest research from elsewhere to support operations across Metro Transit. We aim to extract from complex datasets the knowledge that will improve Metro Transit through recommendations for action.

How your work would contribute to our organization and the Twin Cities region:

Metro Transit is seeking to fill two (2) full time positions for a Data Scientist. The position may be filled at any one of the following three (3) levels outlined below. This position will be located in Minneapolis, Minnesota.

Senior Data Scientist – Advanced professional research and data science work is expected. The Senior Data Scientist has the ability to develop and implement statistical models, create complex visualizations, and coordinate project work. This level of work is distinguished from the other two junior levels.

Data Scientist – At this level you will be expected to perform professional level of research and data science work.

Associate Data Scientist – As an aspiring data scientist, this is an entry level position with directed professional research and data science work.

In any and all of the levels you will apply advanced data manipulation and analytical methods, including machine learning and statistical models, in support of data-driven decision making efforts in all Metro Transit functional areas. Additionally, you will support effective use and communication of work by designing and developing highly visual, interactive and accessible reports and tools for agency staff.

What you would do in this job:

1. Perform statistical modeling and machine learning analysis to guide Metro Transit in all functional areas:

Design and implement probabilistic statistical models (e.g., linear regression, generalized linear regression, mixed models, Bayesian multilevel models) to extract effects estimates from datasets with high-dimensional, nested structure in space and time.
Apply time-series methods (e.g. auto-regressive moving average, smoothing) in support of ridership forecasting and modeling.
Use clustering methods (e.g. k-means, hierarchical tree-based) and regression methods in support of survey analysis for customer satisfaction, rider decision making and choice research, and market segmentation.
Use probabilistic modeling (e.g. logistic regression, survival methods) in support of predictive maintenance planning and other management goals.

2. Perform advanced data analysis research:

Review scholarly articles and technical papers in academic and industry databases/journals.
Coordinate transit research projects with University researchers and collaborate in research where appropriate.
Write literature reviews and papers for internal and external publication.

3. Perform advanced development of interactive data visualization tools:

Use R Shiny, D3.js, similar platforms to develop interactive data visualization and modeling tools in support of analysis of system performance, travel time, ridership, etc. to support service planning and delivery, customer information, and other activities.
Create static and interactive maps to convey spatial patterns and trends.
Meet with internal and external stakeholders to develop and define requirements. Iteratively develop tools.

4. Perform full performance design of systems for data capture:

Extract, collect, clean, and prepare data for analysis.
Create and maintain databases and spreadsheets.
Organize data and results of analytics projects.
Write and maintain metadata for internal and external understanding of data.
Design, implement and utilize advanced data management systems and cluster computing environments to facilitate complex models on very large data sets.

5. Provide limited work direction to Associate Data Scientists and interns (Senior Data Scientist-level).

Provide limited mentoring, coaching, and guidance to Associate Data Scientists, Data Scientists, and interns.

Evaluate the work of Associate Data Scientists, Data Scientists, and interns.

What education and experience are required for this job (minimum qualifications):

Senior Data Scientist
Full Salary Range: $70,845.00 – $100,506.00 annually.

Bachelor’s degree in Statistics, Mathematics, Economics, Analytics, Physics, Biology, Psychology or other related highly quantitative field AND four (4) years or more of experience in the following:

Management of multivariate datasets and creation and evaluation of statistical models
Using the "R" or "Python" programming language
Parsing and cleaning unstructured, structured, and semi-structured data; in the full analytics project life-cycle including communicating results to stakeholders.
At least two (2) years of experience in the development and communication of statistical models. At least (1) year of experience leading analytics projects

OR
Equivalency: Eight (8) years of related education and experience may be substitute on a year to year basis, e.g. additional years of progressively responsible experience or Master’s degree may substitute for two (2) years of experience, or PhD may substitute for four (4) years of experience.

Data Scientist
Full Salary Range: $65,520.00 – $92,955.00 annually.

Bachelor’s degree in Statistics, Mathematics, Economics, Analytics, Physics, Biology, Psychology or other related highly quantitative field AND three (3) years of experience in the following:

Management of multivariate datasets and use of statistical modeling techniques
Using the "R" or "Python" programming language
Parsing and cleaning unstructured, structured, and semi-structured data, in the full analytics project life-cycle including communicating results to stakeholders.
At least one (1) year of experience in the development and deployment of statistical models

OR
Equivalency: Seven (7) years of related education and experience may be substitute on a year to year basis, e.g. additional years of progressively responsible experience, or Master’s degree may substitute for two (2) years of experience, or PhD may substitute for four (4) years of experience.

Associate Data Scientist
Full Salary Range: $60,611.00 – $85,987.00 annually.

Bachelor’s degree in Statistics, Mathematics, Economics, Analytics, Physics, Biology, Psychology or other related highly quantitative field AND two (2) years of experience in the following:

Management of multivariate datasets and use of statistical modeling techniques
Using the "R" or "Python" programming language
Parsing and cleaning unstructured, structured, and semi-structured data, in the full analytics project life-cycle including communicating results to stakeholders

OR
Equivalency: Six (6) years of related education and experience may be substitute on a year to year basis, i.e. additional years of progressively responsible experience or Master’s degree may substitute for two (2) years of experience, or PhD may substitute for four (4) years of experience.

What additional skills and experience would be helpful in this job (desired qualifications):

Experience with transit or transportation data.
Experience with collaborative coding and git workflow.
Experience writing SQL and managing relational databases.
Experience building hierarchical multilevel models in a Bayesian statistical framework.

What are the knowledge, skills and abilities for this job:

Knowledge of:

Statistical analysis techniques (multilevel regression or mixed model analysis; survival analysis; time-series modeling, etc.)
Academic/industry research methods
Database systems design and maintenance
Bus and rail transit systems operations principles and practices
Machine learning models (e.g. Random Forests, Support Vector Machines, Neural Networks)
Web-based interactive visualization and modeling tool development
Cluster/parallel computing methods

Skills in:

Project management (organization, administration, and completion of projects)
Intermediate level applied mathematics and statistics
Advanced level in a statistical analysis software package (SPSS, SAS, STATA, R, Python, etc.)
Intermediate data visualization using e.g. ‘ggplot2’ package in R, D3 in JavaScript.
Intermediate level database design and report writing
Skills in data mining with structured, unstructured, and semi-structured data

Ability to:

Read and understand complex academic and technical papers
Write summary reports, technical papers, and literature reviews
Utilize statistical analysis to analyze data, identify trends, and determine root causes of trends
Guide and lead full analytics project management life-cycle ranging from defining business objectives to communicating, deploying, and training business users on analytic solutions
Lead, guide, and mentor Associate Data Scientists, Data Scientists, and Interns

What you can expect from us:

We offer the opportunity to make a difference and positively influence the Twin Cities metropolitan area.
We encourage our employees to develop their skills through on-site training and tuition reimbursement.
We provide a competitive salary, excellent benefits and a good work/life balance.

More about why you should join us!

Additional information:

Senior Data Scientist
Union/Grade: Non-Represented/ H
FLSA Status: Exempt
Safety Sensitive: No

Data Scientist
Union/Grade: Non-Represented/ G
FLSA Status: Exempt
Safety Sensitive: No

Associate Data Scientist
Union/Grade: Non-Represented/ F
FLSA Status: Exempt
Safety Sensitive: No

What your work environment would be:
Work is performed in a standard office setting.
The responsibilities listed are typical of the positions included in the job classification; however, not all duties are necessarily performed by each specific position. Reasonable accommodations may be made to enable individuals with disabilities to perform the essential duties of the position. Regular attendance is an essential responsibility.

What steps the recruitment process involves:

We review your minimum qualifications.
We rate your education and experience.
We conduct a structured panel interview.
We conduct a selection interview.

Once you have successfully completed the steps above, then:

If you are new to the Metropolitan Council, you must pass a drug test and a background check, which verifies education and employment, covers driving record (if applicable to the job) and any criminal record. If you have a criminal conviction, you do not automatically fail. The Metropolitan Council considers felony, gross misdemeanor and misdemeanor convictions on a case-by-case basis, based on whether they are related to the job and whether the candidate has demonstrated adequate rehabilitation.

If you are already an employee of the Metropolitan Council, you must pass a criminal background check if the job you’re applying for is safety sensitive, is a supervisory or management job, is in the Finance, Information Services or Human Resources departments, or has access to financial records, files/databases, cash, vouchers or transit fare cards.

IMPORTANT: If you make a false statement or withhold information, you may be barred from job consideration.