Yuning Liu Email & Phone Number

Seattle, Washington, United States

Buying a home does not have to feel complicated. Our simplified approach helps you search, buy, and move in—all without having to stumble through the traditional process. We brought our local experts together, giving you a team of research analysts, loan officers, and tour agents—all under one roof—including a dedicated Flyhomes Agent to guide you every step of the way. That is guaranteed funds for the seller, making your cash offer even more competitive.Responsibilities:• Worked as Data Engineer in extraction data and preparing data according to business requirements. • Used Pandas, NumPy, Seaborn, Tensorflow, Pytorch, Matplotlib, Sci-kit-learn, and NLTK in Python for developing data pipelines and various machine learning algorithm • Employed statistical methodologies such as A/B tests, experiment design, and hypothesis testing.• Implemented Apache Airflow for authoring, scheduling, and monitoring Data Pipelines• Worked with commercial data mining tools such as R and Python depending on job requirements. • Performed K-means clustering, Multivariate analysis, and Support Vector Machines in Python.• Performed Data Profiling to learn about behavior with various features such as data pattern, location, date, and Time.• Worked with different data sources like HDFS, and Hive for Spark to process the data.• Performed Logistic Regression, Classification, Random Forest, Decision Tree, and SVM to classify package is going to deliver on time for the new route.• Worked on Deep learning platforms such as TensorFlow and AWS ML.• Designed various scalable systems using Hadoop technologies in various environments. • Optimized Hive queries using best practices and the right parameters and using technologies like Hadoop, YARN, Python, and PySpark.• Created several types of data visualizations using Python and PowerBI.• Created SQL tables with referential integrity and developed advanced queries using stored procedures and functions using SQL server management studio.

Seattle, Washington, United States

The project involves developing an Internet traffic scoring platform for ad networks, advertisers, and publishers. The platform would use a combination of rule-based algorithms, site scoring, keyword scoring, lift measurement, and linkage analysis to evaluate and score website traffic. This would allow ad networks, advertisers, and publishers to better understand the quality and potential value of the traffic to their websites, which can help them make more informed decisions about where to advertise, what content to create, and how to optimize their websites. The platform would help to optimize their strategies, make better-targeting decisions, and improve the return on investment of their advertising campaigns.Responsibilities:• Gathered requirements based on the business problem, and developed and implemented advanced analytics including optimization, prescriptive analytics, and machine learning algorithms using Python, SQL, and Rest API.• Involved in Data Manipulation & Visualization, Web Scraping, Machine Learning, Deep learning, Python programming, SQL, GIT, Unix Commands, NoSQL, MongoDB, and Hadoop. • Involved in Setting up storage and data analysis tools in Amazon Web Services cloud computing infrastructure. • Used pandas, NumPy, seaborn, scipy, Pytorch, matplotlib, Scikit-learn, and NLTK in Python for developing various machine learning algorithms. • Used A/B testing, multivariate testing, and conversion optimization techniques across digital platforms.• Guide the development team working on PySpark as an ETL platform• Developed programs in Spark to use on applications for faster data processing than standard MapReduce programs.• Built models using Statistical techniques like Bayesian HMM and Machine Learning classification models like XG Boost, SVM, and Random Forest. Communicated new or updated data requirements to the global team.

Seattle, Washington, United States

Our project was to design and develop an Enterprise Reporting System for financial services, to support the portfolio management and performance analysis of the Credit Card business with various reward offerings, and to design a web-based end-user interface.Responsibilities:• Involved in gathering, analyzing, and translating business requirements into analytic approaches. • Worked with Machine learning algorithms like neural network models, Linear Regressions, SVMs, and Decision trees for the classification of groups and analyzing most significant variables. • Converted raw data to processed data by merging, and finding outliers, errors, trends, missing values, and distributions in the data. • Developed near real-time data pipeline using spark• Performed data analysis, visualization, feature extraction, feature selection, and feature engineering using Python.• Worked on Clustering and factor analysis for the classification of data using machine learning algorithms. • Used Power Map and Power View to represent data very effectively to explain and understand technical and non-technical users. • Responsible for developing data pipeline with AWS S3 to extract the data and store it in HDFS and deploy implemented all machine learning models. • Worked on Business forecasting, segmentation analysis, and Data mining and prepared management reports defining the problem; documenting the analysis, and recommending courses of action to determine the best outcomes. • Created SQL tables with referential integrity and developed advanced queries using stored procedures and functions using SQL server management studio. • Developed framework for converting existing Power enter mappings to PySpark (Python and Spark) Jobs.• Worked with risk analysis, root cause analysis, cluster analysis, correlation and optimization, and K-means algorithm for clustering data into groups. • Coordinated with data scientists and senior technical staff to identify clients' needs.

Seattle, Washington, United States

The goal of the project was to leverage data to improve their business strategy as well as transform their digital channel into an active business model that no longer is an expense but also helps businesses to save cost and increase return on investment by devising a digital strategy for your business with detailed explanation and analysis on digital performance such as website traffic and visitor behavior patterns.Responsibilities:• Performing Data Validation /Data Reconciliation between disparate source and target systems for various projects. • Identifying the Customer and account attributes required for MDM implementation from disparate sources and preparing detailed documentation. • Performed data cleaning and feature selection using the MILib package in PySpark and working with deep learning frameworks.• Prepared Data Visualization reports for the management using R. • Used R machine learning library to build and evaluate different models. • Utilized a broad variety of statistical packages like R, MLIB, Python, and others.• Performed data cleaning using R, filtered input variables using the correlation matrix, step-wise regression, and Random Forest. • Performed Multinomial Logistic Regression, Random Forest, Decision Tree, and SVM to classify package is going to deliver on time for the new route. • Provides input and recommendations on technical issues to Business & Data Analysts, BI Engineers, and Data Scientists.• Created and maintained technical documentation for launching the Hadoop cluster and for executing Hive queries.• Segmented the customers based on demographics using K-means Clustering. • Used T-SQL queries to pull the data from disparate systems and Data warehouses in different environments. • Extensively using MS Excel for data validation. • Generating weekly, monthly reports for various business users according to the business requirements.

Shanghai, China

China CITIC Bank is an organization with a full range of products and services, focused on specialty program business. The major line of business is providing credit lines, overdrafts, and funds management. A Data warehouse was created to give the desired report to different clients.Responsibilities:• Aided Relationship Managers in conducting credit analysis on the syndicated term loans and revolving credit facilities for 11 public companies from different industries, including preparing executive summaries, populating financial statements, and performing ratio analysis• Prepared credit application packages including financial analysis, financial projections, operating analysis, and industry analysis of corporate clients for the Head Office’s credit committee to review and approve• Developed models to assess trends, project needs, surface challenges, and estimate costs• Automated processes which reduced 50% of manual resources and doubled the efficiency• Created pro forma cash flow projections in Excel to forecast clients’ operating revenue, expenses, and debt metrics and measure the clients’ repayment ability• Prepared the annual review of credit applications by updating their financial performance to recent quarters and cash flow projections.• Identified and analyze stakeholders and subject areas.• Participated in Business Analysis, talking to business Users and determining the entities and attributes for Data Model; identified and determined physical attributes and their relationships through cross-analysis of functional areas.• Identified and analyzed source data coming from SQL server and flat files.• Evaluated and enhanced the current data model as per the requirements• Performed Data, profiling, Validation, and Integration.

• Used pandas, NumPy, Seaborn, SciPy, matplotlib, sci-kit-learn, and NLTK in Python for developing various machine learning algorithms. • Participated in all phases of data mining; data collection, data cleaning, developing models, validation, visualization, and performed Gap analysis. • Programmed a utility in Python that used multiple packages (SciPy, NumPy, pandas).• Converted the data mart from Logical design to Physical design, defined data types, Constraints, and Indexes, generated Schema in the Database, created Automated scripts, and defined storage parameters for the objects in the Database.• Performed Data cleaning process applied backward - Forward filling methods on a dataset for handling missing values.• Defined various facts and Dimensions in the data mart including Fact fewer Facts, Aggregate, and Summary facts.• Reviewed source systems and proposed data acquisition strategy.• Designed and Customized data models for Data Mart supporting data from multiple sources in real-time.• Designed the Data Mart defining Entities, Attributes, and relationships between them.• Data transformation from various resources, data organization, and features extraction from raw and stored. • Researched, evaluated, architected, and deployed new tools, frameworks, and patterns to build sustainable Big Data platforms for clients.

Master'S Degree, Business Analytics

Bachelor Of Science - Bs, Chemistry