Jeff C. Ho Email & Phone Number

Austin, Texas, Us

- Set and executes strategy for measuring who gets hired on Indeed, spearheading novel data collection efforts collectively adding millions of signals for building new models and products- Develop and deploy hire probability models across different surfaces (Search, Recommendations, Bidding, Experimentation)- Lead team of 12 Data Scientists, Engineers, and APMs, setting product vision and sprint priorities

Austin, Texas, Us

Denver, Colorado, Us

- Orchestrated a product plan to develop and launch a new data product targeted toward retailers, investors, and OOH advertisers, growing first $200k annual recurring revenue (ARR) in 3 months- Managed the continued operation and optimization of an existing data product with $5MM ARR, the output of a Learning to Rank algorithm built using Spark in Scala and Python- Performed deep technical analyses in PySpark on quality metrics for guiding optimization roadmap- Set priorities for 3 senior ML engineers by synthesizing business need from go-to-market teams- Directly managed 3 data analysts to inform product decisions, QA pipelines, and build dashboards

Denver, Colorado, Us

Manhattan, New York, Us

- Built an end-to-end machine learning pipeline for collection, training, and deployment to predict real-time bids in programmatic advertising auctions using AWS SageMaker with a custom Docker container - Model pipeline is deployed on a per-client basis and consistently predicts likelihood of conversion with AUC > 0.85 on out-of-sample test data

Manhattan, New York, Us

Focusing on clean brands (i.e., good for environment, health and sustainability), I optimized digital advertising spend/performance for clients looking to reach the right audiences efficiently using data-driven approaches. - Reduced cost per site visit for an online direct-to-consumer brand campaign by 50%, and improved customer acquisition cost for another business-to-business performance campaign by 60%- Designed and implemented A/B tests across multiple ad platforms to generate insights about creative, audience, or targeting strategies, and to measure incremental revenue plus brand lift- Automated campaign reporting using SQLAlchemy in Python, reducing weekly time spent by 80%

San Francisco, Ca, Us

- Helped organic trade associations target advertisements to user segments by predicting likelihood of purchasing organic produce based on past shopping history- Reduced irrelevant ads by 40% by combining product recommendations from collaborative filtering using LightFM with logistic regression with user characteristics using scikit-learn- Visualized purchase likelihoods and recommended products in a web app built using Streamlit and deployed on Amazon EC2

New York, Us

- Led the ideation, technical development, and launch of two disaster analytics data products for government and humanitarian users, growing product revenue 5-fold to >$500,000- Wrote production code in bash for scaling back-end automations using Google Cloud (cron, Pub/Sub) that performed real-time model deployment on satellite imagery in Python- Designed front-end dashboard for delivering insights, guiding front-end developer in Angular- Grew product deployment team from zero to 3 by hiring first three scientists and analysts- Delivered data-driven recommendations that led to the decision for a humanitarian user to relocate 7,000 refugees from a flood-prone area [bit.ly/RefugeeFlooding]

New York, Us

Stanford, Ca, Us

• Created a new three-decade data set of algal bloom occurrence in 76 lakes globally from Landsat using the Google Earth Engine Python and JavaScript APIs, exploring worldwide trends and drivers• Developed a novel method for validating remote sensing algorithms used to identify algal blooms• Presented research findings with six oral presentations and two posters at various academic conferences and at a United Nations Workshop on transboundary water cooperationReceived a 2015 Google Earth Engine Research Award for cutting-edge geospatial analysis based on proposed research.Named a 2014 Rising Environmental Leader Fellow by the Stanford University Woods InstitutePublications: Ho, J.C, A.M. Michalak, and N. Pahlevan. (2019). "Widespread global increase in intense lake phytoplankton blooms since the 1980s." Nature. 574(7780): 667-670.Ho, J.C. and A.M. Michalak. (2019). "Exploring temperature and precipitation impacts on harmful algal blooms across continental US lakes." Limnology and Oceanography. 65(5): 992-1009.Ho, J.C. and A.M. Michalak. (2017). "Phytoplankton blooms in Lake Erie impacted by both long-term and springtime phosphorus loading." Journal of Great Lakes Research. 43(3): 221-227Ho, J.C., R.P. Stumpf, T.B. Bridgeman and A.M. Michalak. (2017). "Using Landsat to extend the historical record of lacustrine phytoplankton blooms: A Lake Erie case study." Remote Sensing of Environment. 191: 273-285Ho, J.C., and A.M. Michalak. (2015). “Challenges in tracking harmful algal blooms: A synthesis of evidence from Lake Erie.” Journal of Great Lakes Research. 41(2), 317-325.

Stanford, Ca, Us

• Developed algorithms for monitoring household water access with digitized walking paths from DigitalGlobe satellite imagery in Africa and Central America using Python in ArcGIS • Analyzed multi-dimensional household survey data on rural water use to compare and contrast different metrics for assessing global water accessPublications:Ho, J.C., K.C. Russel and J. Davis. (2014). “The challenge of global water access monitoring: evaluating straight-line distance versus self-reported travel time among rural households in Mozambique” Journal of Water and Health. 12(1), 173-183.

Waterloo, Ontario, Ca

• Developed algorithms for dust cloud segmentation in time- and space-varying satellite infrared images over Sub-Saharan Africa, using Otsu’s method in Matlab• Compared and evaluated the effectiveness of nine different methods for differentiating cloudpixels from background pixels, mostly based on the rate of change of the infrared signal

Westminster, Co, Us

• Developed and executed detailed plans testing integrated GPS technology for environmental problems dealing with mapping and GIS• Conveyed complex product issues succinctly and thoroughly to multi-national development team through the extensive use of oral and written communication• Performed statistical data analyses testing GPS receiver accuracy and reliability• Engaged local universities and businesses in dialog to facilitate educational partnerships

Doctor Of Philosophy (Ph.D.), Civil And Environmental Engineering

Master Of Science, Civil And Environmental Engineering

Bachelor'S, Honours Environmental Engineering With Water Resources Option

Bachelor'S, Environmental Engineering