Apply on Employer Site

County of Los Angeles · 5 months ago

PREDICTIVE DATA ANALYST / EMERGENCY APPOINTMENT HOMELESSNESS

Los Angeles County, CA

Contract

Onsite

Entry Level

2+ years exp

The County of Los Angeles is seeking qualified candidates to fill emergency Predictive Data Analyst vacancies related to the homelessness crisis. The role involves maintaining and analyzing data assets, utilizing machine learning techniques to support data-driven program design, and producing dashboards and reports to aid program managers.

CommunitiesGovernmentNon Profit

Comp. & Benefits

Responsibilities

Assists with the design, development, and planning implementation of evaluation services and highly complex data science projects by collaborating with the Sr Data Scientist and SAPC program staff, contracted providers, and other stakeholders, that are needed to drive planning, and policy decisions to reduce cost, promote quality of care, and implement value-based SUD treatment and prevention services including but not limited to forecasting utilization and cost, cost/finance analyses, cost-effectiveness analyses, and predictive/prescriptive data modeling to identify investment prioritization, design interventions, and measure outcomes, identifying existing and emerging trends and gaps in care to maximize revenue, and to reduce the cost of unnecessary waste and over/under utilization of services

Conducts predictive data assignments for Behavioral Health Quality Improvement Projects (BHQIP) and performance improvement projects (PIPs) mandated by the state and External Quality Review Organization (EQRO) by identifying areas for improvement within SAPC's programs and services through complex data analysis and performance metrics

Collaborates with Sr Data Scientist, program managers, patients, stakeholders, and provider network members to develop and implement strategies to address identified areas of improvement and enhance program effectiveness and efficiency

Assists with the program performance evaluation, ensuring adherence to regulatory requirements, fidelity, outcomes and effectiveness of various funding programs and grants including CalWORKs and General Relief, Measure H, Behavioral Health Bridge Housing (BHBH), Assembly Bill (AB) 109, Care First and Community Investment, Block Grants, and state or federal grant awards

Utilizes advanced statistical techniques and methodologies to analyze large-scale service utilization data (e.g., service utilization by CPT codes, level of care, and provider type, and agency) to predict at-risk and high utilizers and risk performance areas, and initiating other projects

Utilizes big data collected via Sage in addition to Census, and Medical Eligibility Data System (MEDS) data to conduct predictive/prescriptive data modeling that will inform SAPC leadership to make better financial, business, policy and operational decisions in managing costs, utilization, and quality of care as well as financial risk management

Qualification

Machine LearningPredictive AnalyticsData ManagementStatistical AnalysisData VisualizationQuantitative ResearchCollaborationCommunicationProblem Solving

Required

A Bachelor's degree from an accredited college or university in a field of applied research such as Data Science, Machine Learning, Mathematics, Statistics, Business Analytics, Psychology, or Public Health that included 12 semester or 18 quarter units of coursework in data science, predictive analytics, quantitative research methods, or statistical analysis

Two (2) years of experience in the application of techniques of machine learning, predictive analytics, data management, and hypothesis-driven data analysis to complex experimental designs leading to actionable findings and recommendations

A valid California Class C Driver License or the ability to utilize alternative method of transportation when needed to carry out job-related essential functions

Four (4) years of experience with responsibility for planning, designing, conducting, and evaluating research projects involving the application of techniques of machine learning, predictive analytics, data management, and/or hypothesis-driven data analysis to complex experimental designs leading to actionable findings and recommendations