Correct the grammar on below points.

• Larry provided Solution architecture and design expertise for theAircraft Reliability & Maintainability system ( ARMS), In- Service Data Program (ISDP). Larry was the lead Statistical Programmer in support of the In-Service Data Program (ISDP), which analyzed airlines data (Spec2000 and csv files), validated the data against Boeing and ATA (Airline Transportation Association) requirements, then designed, built, and tested pipeline to load the data into Boeing Teradata database. (ARMSMART). Larry created artifacts that documented the business requirements and technical solutions, the Ingestion pipelines which included logic to cleanse airline data (warnings, errors, enrichments, etc.) and produce load reports for customer review and action on data quality. By working with and leading a team of Data Architects, DBAs, engineers Business focals, system architects, roughly 25 IT Team member, wrote scripts on Statistical programming and lead 7 Statistical programmers and create idea and SAS script on how to use JCL on the mainframe to read airline data and convert all mainframe JCL in the Statistical algorithm to window scripts and lead the business requirements meeting and documented all the required documents. This project involved Data understanding, Data pre-processing, Data warehousing and Data load. On this project, Larry achieved success in this project, by lead the team and, by provided my Mainframe knowledge, SAS, complex technical and professional skill sets to convert all the Mainframe scripts into a Windows environment and sunset the mainframe, also converted all the manual process into Automation process and save a lot of time and budget, lead, and educate the Statistics programmers and functional Analysts team. Currently there they are still using the structure of schema that we built in Teradata schema called (ARMSMART) today. We also have had more airlines join this project more than before.Currently, Boeing revenue producing applications and consumers are now using this project as a Data warehouse for their line-of-business and analytics projects, including SASMO, My Boeing Fleet, MIDOT, OMP, and RSPL. (BCA, BGS, etc.).

• Larry led the programming team of the MIDOT (Maintenance Interval Determination and Optimization Tool) application. MIDOT was developed as a quantitative reliability tool for the development of 787 maintenance program and is required for all the new aircraft maintenance program development going forward from the 787. It uses in service data for specific aircraft components to evaluate reliability.Larry architected both Data and system web applications, and built a data pipeline that includes, Data understanding, Data pre-processing, Data warehousing, Data modeling that attempt to solve complex issues. Larry guided and worked with 8 statisticians, technical architect, and 5 engineers to build and develop this application. This tool helps in the process of determining the suitability of a potential component replacement time for a new aircraft program along with helping to determine any applicable maintenance task for a new maintenance program.

• Larry provided expertise and design skills to build the legacySASMO applications. (SASMO, OMP, ARCS & Monitoring) Statistical Analysis for Scheduled Maintenance Optimization (SASMO) Project. The Maintenance Programs Engineering uses SASMO Application for interval adjustments for failure tasks that required the use of statistical methods for evaluation by OEM and hence SASMO is the tool used to meet this statistical evolution of interval change requirements per IP-44 and provide the interval recommendation to airlines and SASMO project was successfully and got approved by FAA. The SASMO application also contains below applications.
• Optimized Maintenance Program (OMP). The airline maintenance program is typically based on the Boeing OEM MRBR initial scheduled maintenance requirements, which is not customized and uses the worldwide fleet data and a conservative approach to interval selections. The OMP analyzes the customized AMP scheduled maintenance requirements with close to 100% of the operator's own in-service data, thereby customizing the intervals based on their unique in-service experience, reliability and maintenance practices, and operational profile. With that additional efficiencies can be gained, and value created for the operator: Value of the OMP is defined by benefits achieved through implementation of the new OMP program for each airplane in: Check and Interval Escalation Benefit (increase) - Reduced check frequency.

Check Efficiency (increase/decrease)- Increased/decreased # tasks and hours in check, more

findings, repairs Airplane Availability Benefit (increase)- Increased utilization through additional available days to

fly airplane Material Savings (increase) - Reductions in materials and consumables.

• Monitoring project: The objective of the monitoring analysis is a comprehensive review of the performance of the operator's Optimized Maintenance Program, and identification and mitigation of any Optimized Maintenance Program performance issues. Annual monitoring reports are provided for the 5 years after Optimized Maintenance Program implementation that assess the on-going performance of Optimized Maintenance Program changes to ensure an efficient and effective Optimized Maintenance Program. The intent is to validate the effectiveness of the implemented Optimized Maintenance Program interval changes and to identify additional opportunities for maintenance interval optimization.

• ARCS (Automatic Record Categorization System). Engineer is analyzing the airlines data manually. Engineer cannot review airline unstructured data in few hours. So Machine learning modeling is really applicable on this project. The intended of this project is to use a Machine learning system that will utilize an engineer reviewed and categorized the data. The datasets are consisting of Spec2000 aircraft maintenance data. Larry led the team, researched the data usages and built the models for ARCS project with Machine learning algorithm using Data pre-processing, Data understanding, Data warehousing, Data Modeling and Pattern evaluation. This new automated machine learning approach now takes 30mins to 1 hour for what used to take 2 to 3 days of an engineer's time.

• Larry architected both Data and system web application, and built a data pipeline that includes, Data understanding, Data pre-processing, Data warehousing, Data modeling and performs complex technical and professional activities to solve complex issues by researched for the appropriate data and statistical programming technics that were needed for the Legacy SASMO and OMP applications, worked with 8 statisticians' group, technical architect and 5 engineers' groups, he used his expertise of Machine learning and built ARCS and Monitoring Projects

• Larry was the part of Boeing Analytics evaluation team for Product and Services Evaluation criteria. SAS Evaluation - Technical Customer Support /SASMO / Text Mining. (Text Mining, Data Mining, Pattern Discovery, and Predictive Modeling - Advanced Analytics Statistical Tool Evaluation Feeder(SPSS, SAS and IBM Analytics) and Also leads and performed evaluation between paid professional Analytics software ("SAS" and "SPSS") and Open Analytics software ("R" and "Python" programming languages and libraries.)