Case Studies
Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
Steel industry
Projected 25% increase in throughput on the mill floor through Simulation and Optimization
Client Challenge
The client had many steel coordinators on the mill floor making decisions based on heuristic knowledge and spreadsheet-based modeling. Operators were leveraging simple averages to understand possible dwell times and transit times, often overlooking large amounts of available details. Overarching goal was to keep the casting units running constantly and at maximum speed. To do this the plant floor operators needed optimal production schedules to be produced to maximize output.
Our Approach
The Aimpoint Digital team worked within the client Hadoop environment, leveraging Python, Spark, and Pyspark to take advantage of edge computing nodes to implement a Discrete Event Simulation which scaled to compute thousands of probability densities efficiently and quickly. This allowed the team to run a “what-if” style analysis to determine optimal schedules given production requirements. The Aimpoint team was also able to include additional functionality to the client team, allowing them to push JSON files detailing certain scheduled machine downtimes to understand the effect of machine maintenance on optimal production schedules.
Outcome
Reduced total time to complete production schedules an average of 25%, meaning a 25% increase in plant productivity. Client team is now able to query their datalake via API to return optimal schedules and run various “What-if” style scenarios.
Plastics industry
15% yield increase on the mill floor due to explainable modeling techniques
Client Challenge
The client had many machine instances on the manufacturing floor. Each machine operated slightly differently through a variety of factors. Hundreds of variables were being regularly tracked in real time. Operators wanted a visual representation of relationships between variables. Understanding causal mappings between inputs and outputs would allow them to see what actions should be taken to improve output quality.
Our Approach
Leveraging a casual inference type approach to understanding variable relationships as well as linear methods allowed the team to filter out uninformative features and understand directional relationships between available levers and quality. Techniques such as Granger Causality (time series), SHAP values, and PDP plots were extracted to provide both high level and granular level insights in an easy to consume, automated report.
Outcome
Automated reports being delivered routinely to decision makers operating mill floor machinery allowed an increase in plant productivity. Operators were able to understand what machine parameters should be adjusted in order to maximize output quality.
CPG industry
Demand forecasting at enterprise scale for production planning shows 23% improvement
Client Challenge
Erratic demand due to Covid-19 was making business planning difficult and causing large disruptions in supply chain. Client needed to leverage large amount of external information to correctly plan production demand, and at a much higher granularity than previously done. Previous models only predicted production demand at aggregate level in a rolling monthly format, but client required weekly updates at a factory level to bring adaptability in Covid struck production schedules.
Our Approach
Taking large amounts of information into a spun-up cloud VPS instance allowed parallelization across numerous vCPUs. This information was then restructured to leverage regression style approaches to time series forecasting with deep learning networks built in Tensorflow. Containerization in docker and model versioning and hosting via API allowed rapid scoring and training while minimizing compute costs.
Outcome
The comparison between the new Covid-19 robust model and the spreadsheet based model previously used showed a 23% reduction in MAPE and levels of detail not previously possible. This allowed individual plants to generate optimal plans for production inventories.
Transportation Industry
15 DMAs identified with 10+ opportunities for site building, 565 store locations identified with prime conditions
Client Challenge
A leading drone flight services provider was tasked with identifying 155 store locations at which to pilot last-mile deliveries for a large superstore chain. They needed to identify sites with high financial potential to prioritize. Alternative delivery methodologies such as unmanned aerial vehicles are on the cutting edge of transportation innovation, and as a result, they are challenged with exploring new markets without formalized infrastructure, data, and precedent. Due to the scale of the project and having to consider several thousand stores across the country, a data-driven approach was needed.
Our Approach
The Aimpoint Digital team developed a model accounting for 70+ unique factors ranging from population densities to average wind speeds. The metrics were derived from 10 different data sources, normalized, and weighted for DMA and store comparison. The findings were then visualized through 5 configurable dashboards, showcasing ranked locations, satellite views, flight restrictions, competitor locations, and heat maps. The team leveraged Alteryx for the APIs, ETL, and modeling, Tableau for the dashboarding, and Snowflake for storage optimization and automation.
Outcome
The client can build pilot sites in the 15 DMAs that the model has identified as expected to have the highest ROI. Each is concentrated with 10+ store locations with prime conditions, so that one site can serve many stores. 565 stores have been identified as favorable, so that the client can proceed into more difficult markets with a phased approach. The client also now has a centralized knowledge bank to understand how each factor contributes to each location’s potential. The executive and flight operations teams will be able to use the dashboards internally for education and planning, as well as externally in conversation over the next several years with the superstore chain.
Telecommunications Industry
Represent the full customer journey to maintain and grow customer subscriptions
Client Challenge
A client providing communication solutions to consumers across the globe was seeking a way to unify and analyze several types of customer data being regularly aggregated. This process also needed to be automated such that all insights would include the most current data available, and the client be automatically alerted of any discrepancies in the data. The ability to pull insights at both the company and individual customer level was crucial to enabling the client to ensure continual internal expansion, successfully onboard new customers, and provide current customers with tools to find opportunities to grow.
Our Approach
Our team developed several dashboards that utilize different perspectives to highlight the client’s highest priority metrics. Using Alteryx, the 5+ disparate data sources across 50+ clients were blended into one cohesive source that was utilized for customer journey reporting in the form of embedded Tableau dashboards. Automation was developed to ensure mapping across all sources persist over time. The 3 dashboards featured a global view of products and customers by KPIs, a customer deep-dive that pulled financial, operational and contractual information together and a customer timeline view summarizing key points of the last 12 months of the customer interaction.
Outcome
The dashboards provided holistic insight for customers that the company has previously never been able to accomplish. These data solutions have provided sales teams rich insight into customers during negotiations but also in strategic sales and marketing decisions.
Logistics Industry
Business Intelligence to master the complexity of logistics & deliver enhanced customer outcomes
Client Challenge
A $1B+ major global full-service transportation and logistics company with operations spread across North America and globally needed visibility into the operational aspects of its business. As a freight forwarder working with 1500+ vendors to move over 230,000 metric tons for 1.5M customers yearly, mastering complexity was critical to meeting customer expectations. This required the development of KPIs and operational dashboards to convey insight to senior management and stakeholders.
Our Approach
We determined that visibility was required in four key areas: temporal (timeliness, dwell times, middle mile transit time), vendor compliance (proof-of-delivery recording), operational performance (total volume shipped, network burden, etc.), and financial performance (profitability, pricing, cost management, etc.). To convey this insight, our team produced a comprehensive cloud solution producing Tableau dashboards with a backend supported by data engineering in Alteryx, Snowflake & DBT.
Outcome
After deployment of our solution, the client was able to monitor & improve operational performance for its key national level accounts, identify levers to improve the financial performance of its most important transshipment stations, and enhance the customer experience by improving timeliness and compliance.
Private Equity
Private Equity firm can effectively monitor their portfolio company finances
Client Challenge
This private equity firm was struggling to consolidate financial reporting across their 7 portfolio companies. They received monthly reporting in spreadsheets, with little consistency in structure, format and account mapping across subsidiaries. Consolidating reports was a manual process, causing a delay in portfolio-wide performance. There was also no ability to easily audit changes that may have occurred between months. These required the development of a flexible data ingestion process, a robust way to store data that facilitated auditing, and a platform to seamlessly visualize and present financial reporting.
Our Approach
Our team developed an integrated data platform to ingest, store and visualize the portfolio company data. The raw data was standardized using Alteryx, catering for the unique characteristics of each portfolio company’s dataset. A Snowflake data warehouse was developed by our Data Engineering team to model the data from the ground-up. A suite of financial performance dashboards in Tableau were used to disseminate reporting to the private equity company and their subsidiaries.
Outcome
The client now has a single source of truth for portfolio company financials. The ingestion process has significantly alleviated the manual burden in consolidating reporting across their portfolio. The visualization platform has reduced time-to-insight, ensuring that the entire company is viewing accurate, consistent financial reporting within and across portfolio companies. Thanks to the auditing capabilities of the data warehouse model, the client can more easily detect changes made to historical data that were previously obscured by spreadsheet reporting.
Vendor Data Integration
Client Challenge
A mid-sized pharmaceutical company sought to stand up an analytics hub to automate the integration of competitive intelligence data from multiple vendors into one centralized location to enable folks across the organization to gain deeper insight into market drivers and trends through dashboards and visualizations. There had been several requests in the past to compile drug and company competitor profiles with each request often taking multiple weeks of effort to combine, deduplicate, and clean the disparate data sources to ultimately present data that had quickly become stale.
Our Approach
Aimpoint created detailed inventories of all the fields available from the client’s data subscriptions and worked closely with them to identify value-add analytics use cases. We automated the extraction of data and developed a robust data model using a combination of data vault and Kimball dimensional modeling techniques. Additionally, with our upfront understanding of their desired analytics capabilities we were able to identify gaps within the currently available data and assist them in sourcing that information.
Outcome
Through an automated, integrated, and user-friendly data model, end users can utilize drag-and-drop visualization tools to quickly conduct their own investigations and to view underlying trends amongst competitors with reliable and fresh information.
Data Modeling & Reporting
Client Challenge
Due to the questionable veracity of the data being received from portfolio companies, the client wanted to standardize financial and operational reporting. This fledgling firm would spend weeks wrangling the data they received to compile monthly financial packages generally leaving little to no time to make sense of the data or to perform deeper analysis. They needed a process to load trial balances and other operational data straight from the source into a user-friendly data model so they could automatically generate reports that they could trust for better data-driven decision making.
Our Approach
Aimpoint conducted interviews with stakeholders from every team across the entire organization to understand each persona’s data needs and reporting responsibilities as well as their current pain points during their daily processes. From that, we were able to identify data sources, inventory use cases, and prioritize a product roadmap for agile delivery of related dashboards. Through our careful inventory of data sources and products, we developed a holistic and flexible data model for more accurate descriptive analytics while setting the groundwork for advanced analytics.
Outcome
Through a standardized data model, the monthly financial packages which previously took a team of analysts weeks to create can now be automatically generated in seconds. Additionally, the client has instant visibility into adjustments and revisions to trial balances historically through account level audit trails.
