Data Scientist Machine Learning

Senior Data Scientist and Analytics Professional

ALISHER ASHUROV

Email: **************.***@*****.***

Phone: 737-***-****

LinkedIn:https://www.linkedin.com/in/al

isher-ashurov-34a284305/

SUMMARY

Accomplished data scientist with over 12+ years of experience in diverse industries such as United Nations, World Bank, Asian Development Bank and private entities

• Expertise in analyzing large and complex datasets, extracting valuable insights, and developing predictive models using statistical analysis and machine learning algorithms.

• Successfully led cross-functional teams in executing data-driven projects, collaborating with stakeholders to deliver impactful solutions and drive business growth.

• Proficient in working with various data sources, including customer behavior data, sales transactions, genomic data, and electronic health records, to derive meaningful insights and support strategic decision-making.

• Proven track record in applying advanced analytics techniques, such as regression analysis, clustering, natural language processing (NLP), and deep learning, to solve complex business problems. TECHNICAL SKILLS

● Statistics: Statistical Inferencing, Experiments Design, Neural network, Predictive & Preventive ML models, Regression Linear/Logistic Regression, Decision Trees, Ensemble Methods, Random Forests, Support Vector Machines, Gradient Boosting, Bayesian Learning, Principal Component Analysis, Factor Analysis, K-Means, Hierarchical Clustering, Gaussian Mixture Models, Market Basket Analysis, Collaborative Filtering and Low Rank Matrix Factorization, T Test, Chi-Square tests, Stationarity tests, AutoCorrelation tests, Normality tests

● Data Science: Machine Learning, Deep Learning, Data Warehouse, Data Mining, Data Analysis, Big data, Visualizing, Data Modeling, Data Pipeline creation, Gen AI, LLM, Chat GPT, BERT, GAN, Generative AI,

● Databases: MySQL, Hive, Microsoft SQL Server 2014/2012/2008/2005, Teradata, MS Access, SQL Server, Oracle.

● IDE Tools: Jupyter, DBeaver, RStudio, Spyder, Eclipse and Visual Studio.

● Versioning Tools: Git, GitHub

● Cloud and ERP: MS Azure, Azure SQL server, Google cloud & MySQL, Oracle Fusion, MS Dynamics CRM etc

● Analysis and Modeling Tools: MS Access 2000, and dimension tables, Pivot Tables.

● Reporting Tools: Amplitude, Tableau, Power BI, Looker, MS Excel Reports, MS Access Reports

● Operating Systems: Windows, Linux, Unix

● Languages: SQL, R, Python (NumPy, Pandas, SciPy, Sklearn, Matplotlib, Seaborn, Stats models, Tensor flow, Keras)

PROFESSIONAL EXPERIENCE

Role: Consultant Senior Data Scientist

Clients: United Nations agencies, New York, April 2022 – Apr 2024 Key Accomplishments:

● Leveraged advanced SQL querying techniques, data mining to extract, acquire, clean and preprocess large datasets from various multiple sources ensuring data quality and integrity for further analysis and modeling.

● Developed, implemented and deployed machine learning algorithms and statistical models utilizing techniques such as Bayesian HMM, various Machine Learning models including Decision trees, SVM, Random Forest and ensemble methods like XGBoost.

● Created efficient Python utilities, leveraging packages like Numpy, Scipy, and Pandas to streamline data processing and analysis tasks.

● Enhanced Python scripts to seamlessly integrate training data with Azure Cloud Search database, enabling accurate response label assignment for further document classification.

● Effectively implemented A/B testing to improve UI/UX and KPIs

● Spearheaded end-to-end ML projects, including understanding the business need, aggregating data, data exploration, building & validating predictive models, and deploying completed models with concept-drift monitoring and retraining to deliver substantial business impact to the organization.

● Involved in various phases of Analytics using R, Python and Jupyter notebook from Data collection and treatment, analyzing existing internal data and external data, working on entry errors, classification errors and defining criteria for missing values

● Leveraged Python libraries like Pandas, NumPy, Seaborn, Matplotlib, Scikit-learn, Sklearn for developing various machine learning models such as Logistic Regression, Gradient Boost Decision Tree and Neural Network in building predictive models.

● Effectively cleaned and manipulated complex datasets to create the data foundation for further analysis and to generate key insights using tools like MS SQL server, R, Tableau, Excel. Role: M&E Specialist (Data Lead)

Client: United Nations Population Fund, New York, Feb 2018 – Mar 2022 Key Accomplishments:

● Played a pivotal role in all phases of data lifecycle, Data Mining, Data Collection, Data Cleaning, Data Management, Model Development, Validation, Visualization and Performed Gap Analysis

● Spearheaded the development of WizMonitor applications by using PowerApps, Power Query, Power Trigger handled data from various RDBMS and non-RDBMS datasource.

● Handled importing of data from various data sources, performed data control checks and loaded data into HDFS

(Hadoop Distributed File System).

● Led the establishment of CI/CD pipelines, utilizing GitHub for version control and granting our team full ownership of the environment, ranging from infrastructure provisioning to repository maintenance and access management for the development team.

● Oversaw the conduct of 20 surveys and statistical analysis using the available tools such as Python, SPSS, STATA and other statistical tools.

Role: Information Systems Specialist (Data Analytics) Clients: United Nations Population Fund, New York, Jan 2017 – Jan 2018 Key Accomplishments:

● Performed all data transformation, cleaning and validation of collected data using advanced Excel, Power Query and Snowflakes AI tools.

● Developed 4Ws (Who, What, Where, When) dynamic visualization reports with Advanced Tableau and also data statistical analysis with advanced SPSS, Python, EPI-Info and Excel statistical tools.

● Handled importing of data from various data sources, performed data control checks and loaded data into HDFS

(Hadoop Distributed File System).

● Led the establishment of CI/CD pipelines, utilizing GitHub for version control and granting our team full ownership of the environment, ranging from infrastructure provisioning to repository maintenance and access management for the development team.

● Data Cleaning and validation using various data mining tools such as Snowflakes for sourcing from various databases and visualization of data.

● Developed and posted the dynamic data analytical and interactive report developed in Power Bi.

● Trained 45 partner organizations on how to collect, validate, upload and retrieve dynamic reports online. Role: Program Analyst (Lead UN statistical support) Client: United Nations Population Fund, New York, Jan 2011 – Dec 2016 Key Achievements

● Led UN support for the conduct of the nation-wide National Censuses in Tajikistan and Myanmar using the CSVPro, OCR Lingvo and logical checks, commercial scanners and network. The national survey used scanned Optical Character Recognition for data verification and CSV Pro for data collection and aggregation. The SPSS was used to analyze the census data. Oversaw and technical support for the conduct of detailed statistical analysis reports both digital version and monograph, atlas etc

● Technically supported over 30 population related qualitative and quantitative research, surveys based on census and vital statistics data. The surveys used various survey data collection analysis and visualization tools such MS forms, Google forms, SurveyMonkey, CSV Pro, SPSS, Excel, Python, Power BI, Tableau.

● Technically supported the Statistics Department to conduct quarterly labor force and employment surveys, statistical analysis and other statistical researches. Role: Project Management Advisor

Client: United Nations Development Program, New York, Aug 2009 – Dec 2010 Key Achievements

● Established web based reporting information system for Department of Foreign Investments using Google cloud, MySQL, and google sheets.

● Using the analytical tools SPSS and STATA performed statistical analysis for annual Foreign Investment and the UN human index development reports in Tajikistan

● Developed the data visualization reports using Power Query, Power Bi and Tableau Role: Project Manager

Client: Asian Development Bank, Manila, Jul 2005 – Sep 2008 Key Achievements

● Led ADB project support to Government for creating non-bank credit institutions system (i.e. adoption of laws and regulation, association, credit line of 10 mln.)

● Supported the development and training of the non-bank credit institutions in developing financial information system to keep track of the loan and deposit tracking system, training the users and adoption

● Rolled the new financial systems specifically and tailored for non-bank and microfinance institutions. Role: Database Administrator

Client: The World Bank, Washington DC, Oct 2002 – Oct 2004 Key Achievements

● Oversaw the technical needs and maintenance of databases in MS SQL Servers hosted in Windows.Net 24/7,

● Developed SQL scripts, coded stored procedures and provided technical database solutions to API users accessing the database servers

● Kept all database servers updated with security and new feature patches, anti-virus, network access, user profile updates and maintenance

● Migrating and merging databases, data mining and data engineering for using data in WB applications Role: Senior Software Engineer

Client: StaffConnect Inc., Washington DC, Jun 2001 – Apr 2002 Key Achievements

● Developed the StaffConnect telecommunication and WebConnect web application for temporary staffing agencies nation-wide

● Coded, fine-tuned, performed quality assurance and prepared installation packages and user guidelines in MS Studio, ASP.Net, Visual Basic, Access

● Tested the production, documentation of codes, writing manuals and presentation of features to clients

● Provided users technical support and assisted in the sales of the software CERTIFICATIONS

Google Advanced Data Analysts Certificate, Austin, March - August 2024 Results based Management, the World Bank, Tajikistan, Aug 1-30, 2012 Statistics and Demography course, High School of Economics, Moscow, Mar. - Apr 2011 Qualitative and Quantitative Research Methodologies, Washington DC, 2003 Java Programmer, Sun Microsystems, New York, 2001

Client/Server Programming Certificate, Baruch College, New York, March 2001 EDUCATION

Tajik Technological University, Tajikistan, Masters in Economics, 2006- 2011 Baruch College, City University of New York, Mar 2000 - Mar 2001, Certificate of Client-Server Programmer University of Nebraska at Omaha, USA, Certificate of Student Exchange Program, Aug. 1995 - May 96 Kulob State University, Tajikistan, M.S. Computer Science, 1997 - 99, B.A. Foreign Languages,1992 - 97 REFERENCES

Upon Request

Contact this candidate