Sayali Wakle

Checkings, Ameriprise Financial Services

• Served as the lead Business Systems Analyst for the launch of Ameriprise’s new “Checking” product, working closely with cross-functional teams, including product managers, developers, testers, and third-party vendors.
• Interfaced with the product team to gather business requirements, and aligned them with vendor capabilities and REST-based API offerings.
• Conducted vendor analysis and API integration planning to ensure alignment with Ameriprise's functional and technical needs.
• Led Joint Application Development (JAD) sessions to define service flows, and design data proxy and data provider APIs for seamless orchestration.
• Designed end-to-end system flows using Lucidchart, detailing the integration between the UI, internal services (D&S), and vendor services.
• Created detailed API specifications using Swagger (YAML format), and provided comprehensive walkthroughs to Java development teams.
• Collaborated with QA teams to develop test scenarios (happy and negative flows), and led walkthroughs to ensure accurate testing of service interactions.
• Authored complex SES (System Engineering Specification) documents to generate skeleton code and object structures for development teams.
• Partnered with product counterparts to document and refine business and system requirements throughout the project lifecycle.

Key Achievements:

• Successfully launched three pilot phases of the 'Checking' product.
• Independently delivered major features such as Zelle, Bill Pay, and Debit Card Maintenance for Pilots 2 and 3.
• Met aggressive deadlines and consistently delivered high-quality solutions under tight timelines.
• Quickly ramped up on new technologies and took full ownership from the second pilot onward.

Rx Analysis, Walgreens

• Prepared the universal base dataset from raw data sources with the help of Databricks SQL, which helped to build the YOY and MOM data for Power BI reporting. This activity helped the client gain a better understanding of the data for the dynamic period.

Demand Forecasting, AEO

• Being a crucial part of the Rapid Insight Team, we created a new segmentation, 'Accuracy Metric Goal,' to evaluate the accuracy performance of the demand forecasting model and its reliability. Which was then presented to clients and stakeholders with a live Tableau dashboard.

Dynamic Inventory Analytics, Walmart

• Build day-to-day insights on opportunity assessments of inventory items and CX Score. Performed in-depth exploratory analysis to assess opportunities on items using KPIs like pre- and post-sub fill rates, GMV loss due to nil picks, customer rejections, etc. with the help of GCP SQL.

Roles and Responsibilities:

Team Management: Allocation and collation of the tasks to/from senior management and team members basis the inflow volume. Also, responsible for daily connections with clients and coordination with the offshore and onsite teams.

Logic Building: Building SQL queries, logic, and solving any data blockers with the help of research and brainstorming sessions. Data Visualization: Generated reports and views for analysis and forecast understanding on Tableau.

Optimization: Revised, modularized, and updated old code repository to optimized development standards, reducing operating costs and improving functionality.

Customer Analysis, Better

Worked on a key marketing project for targeted customers, which was based on the unsupervised ML algorithm 'KMeans,' as it helped to track down the targeted audience for a better conversion rate. By using the Elbow Curve method, the optimal number of clusters (K number) was decided.

Customer segmentation, Better

Using SQL, segmented the customer base into multiple groups for home loan consideration. Groups were defined based on multiple attributes, such as FICO score, income, existing EMI, etc. Every segmented group would then be offered and approached accordingly.

Roles and Responsibilities:

Logic Building: Customer segmentation logic was built from scratch to understand and evaluate the loan applications.

Stakeholder Connect: Connecting with U.S. stakeholders daily for follow-ups, updates, and improvements in projected results.

Team Management: Organizing daily meetings with the team, and distributing the daily tasks and data to the team.

Health Insurance (In-house Project):

Machine Learning Model based on Random Forest Algorithm was used to predict potential renewal customers at every quarter with help of Python codes. Model was tuned timely to produce 76-82% of accuracy. Model accuracy was measured by the methods like OOB Score.

Roles and Responsibilities:

• Use predictive analytics and machine learning models to facilitate forecasting of business demand.
• Opportunity analysis by identifying patterns in the data.
• Presenting results with National Heads for future strategies.
• Identifying the opportunity for implementation of similar ML models in different business scope like Fire, Marine and Motor etc.