Data transferred through SFTP, ingested into IIP. Data models & Rules design – based on Hive & Spark SQL models were set-up for all rules and for each country (27x2 for initial release in 6 weeks & 46rules x 17 countries for second release in 12-14weeks)
Configuration table feature of IIP was leveraged to provide finance super user community to change the parameters to incorporate country specific filter-in/out criteria which may change over time.
End-to-end data flow within IIP is completely automated through schedulers
Simple & intuitive Hawk-Eye Cockpit built for business users with color-coded outputs, and click-drill-download option to help easy focus & action during time critical month-end Enhanced UI was delivered in second release, consisting of download-to-spreadsheet, graphical view of short-term and long term trends, search & filter on different parameters.
Purpose of addressing data quality issues through the month vs only during month-ends is already being served with Active daily use by 75% end-users in markets; 100% key users touch at least once a week. Flexibility to Super-Users to make country specific configuration changes without lengthy IT-Change Management process
Infosys Information Platform, which powers HawkEye, is being actively considered by client stakeholders for other key needs. Real-time analytics to identify Sales Order gap identification just before stock-pick-and-deliver operations.
Infosys performed near real time aggregation and enrichment of parcel scans data. Early view of the expected parcel volume in depots and in fields. This was instrumental in enabling them for proactive resource planning.
Persona based dashboards: depot, client manager, field manager, and executive, parcel shop, providing real time view and highlighting underperforming nodes in the network under their control.
Volume metrics such as total volume in the network, expected vs actual volume at each node with drill down ability, carry forward volume from past, new volume added in day, number of parcels out for delivery or already delivered and many more. Ability to filter the metrics based on various parcel attributes. Drill down from org level view to parcel level.
Integration with LDAP for authentication and role based access for tight security.
Near real time visibility of expected parcel volume in the nodes enables operations and field teams for proactive resource planning and optimize resource utilization.
Real time view of Expected vs Actual performance helped in improving the service delivery. The laggards, highlighted in red, attract operations team’s attention immediately and direct their focus on clearing off bottlenecks in network parcel traffic. This was not possible earlier.
Real time and interactive view of all parcel volume metrics compared to day old reports in earlier world.
Close to 200 sensors are embedded in each of these vehicles to feed information about both the vehicle and the terrain which is sent back to a remote operations center. Each truck has 400 data points continually sending out information on things such as temperature, vibrations, and tyre pressure.
Data derived from the sensors was streamed into IIP at the rate of 27,000 messages/ second through KAFKA. A mathematical model developed in Apache Spark was applied on this data to derive the probability of equipment failure or if the equipment needs to be replaced or if the machines are in order.
Processed data is overlaid on the 'world map' – a native HTML5 application built on top of IIP. The detailed information can be drilled down by clicking on the color codes.
The IIP-based solution offered enabled data processing in real-time, and was completely elastic and scalable. This supported the client's business plan to increase their fleet of unmanned trucks by more than 300% with corresponding increase in sensor data loads.
Real-time analytics helped get a clear view on aspects like adjustments to production schedule, spare part order release, maintenance schedule, energy costs, machine availability and reliability and optimizedasset utilization. Predictive maintenance resulted in reduction in machine breakdowns with significant improvements in downstream supply chain operation efficiency and business profitability.
In order to eliminate unnecessary locomotive braking events IIP examined the locomotive brake data in combination with engineer characteristics, wayside data streams, maintenance zone information, environmental and atmospheric data and PTC signal data.
PTC braking event and weather data was ingested into IIP on AWS cloud. Text analytics, and a delay event prediction model was built using R and reporting/ visualizations in Tableau.
Different types of analysis were done, such as analysis of locomotives by PTC profile and attributes involved in braking events and providing a 360 degree view. Pareto analysis of Target Type of braking events, basic text mining (N-Gram)/word cloud on delay comments and locomotive delay prediction was also done.
IIP enabled real-time data collection of PTC running into 100s of TB and then real-time prediction based on this data.
IIP helped predict failures with higher accuracy in order to increase the velocity by 1MPH which can result in $200 million revenue. This also helped client's asset utilization increase from 45% and reduce the overall assets for the current demand.
Over 20 data files with finished goods data for both international and domestic sales (shipment data, sales data and product master) were ingested into the IIP data store.
Over 50 models were created into the IIP data lake to bring all the data together at item and UPC level and calculated the sales (LTM), average batch size, profit, and YOY sales increase, ACV for distribution and velocity. Threshold values were established for each of the above metrics (guardrails) to identify the SKUs that pass or fail these guardrails.
Multiple outputs were created in Tableau as a visualization tool. Interactive what-if scenarios analysis (for changing the threshold values) was also provided.
Identified a list of SKU failing most guardrails and initiate the business process to address the issues or drop the SKUs.
An automated SKU rationalization process was implemented based on IIP to identify the non-performing long tail of SKUs. This process can be repeated on demand. This enabled the client to effectively focus on winning SKUs, drive operational efficiency and procurement savings. Apart from the SKU rationalization, further reports of sales performance and predictive analytics can be developed on top of the data platform.
A 5-node AWS cluster was provisioned and installed. IIP was configured for out–of-stock analysis as a PoC project. Sample data from retail stores for 5 weeks at item and register level (5.7 million rows) was ingested into HDFS using IIP's Data Ingestion tools.
The IIP toolset enabled creation of on-demand schemas (models) to access data as well as data wrangling. The historical probability at item, store, and register level was calculated and prediction was run using R based binomial and geometric distribution model to predict out-of-stock.
A visual dashboard was developed in Tableau to demonstrate out-of-stock probability by store/ by hour/ by day/ by item. To demonstrate scalability PoS data was simulated for a retail store chain for 5 years (350 million rows).
From no capability to business insights in just 3 weeks, IIP enabled the client to validate business hypothesis quickly, along with a needful environment to run multiple experiments at the same time for existing data in the platform. An end-to-end PoC project (from AWS cluster provisioning, IIP installation to delivering final insights) was delivered in 3 weeks.
For out-of-stock analysis, IIP demonstrated the ability to drill down to details of the stores with potential out-of-stock to granular level of store, item and register level. It had the ability to filter by various store and item attributes for analyzing the out-of-stock issue.
PoS data from fuel and convenience stores and master data feeds extracted from source systems were loaded into Hadoop/ HDFS using IIP's self-intuitive data Ingestion UI features. Overall 12.5 million rows were ingested in less than 4 minutes.
Leveraged the IIP Data Explorer GUI toolset to model on-demand schemas (based on Spark SQL queries at the backend) to extract data from HDFS and to perform arithmetic calculations; calculated values were pushed to HIVE tables. Materialized views on POS category, subcategory and item level were populated in 30 seconds on average for 1.5 million records.
A visual dashboard was developed in Tableau to demonstrate various insights such as profit by Item level, profit contribution margin (percentage), sales variance(percentage) etc. Data retrieval using Spark was achieved in 0.32 seconds on an average.
A Big Data lake and an advanced analytics environment were implementedbased on IIP that enabled client to derive business insights quickly, within weeks.
IIP Demonstrated that it can augment the EDW by processing huge data sets and combining or joining data from disparate systems as required to fulfill all the needs for intermediate data lake for a detailed level reporting. This eliminates the need for a separate data mart which was required otherwise; and at a substantially reduced cost.
The single day SAP data in the form of pipe delimited files for customer order information – daily logs of order received (size ~7 MB/ 32K records), Zmarc, the snap shot of the available quantity for each plant and material (size ~8 MB/ 34K records) and product hierarchy, the static table containing all the information about materials/products (size ~ 10 KB) was simulated for 365 days and ingested in the Spark shell.
Java UDF was used to calculate the cumulative sum of the quantity ordered column in the order Information table. The cumulative quantity was compared with Zmarc quantity (available quantity) and the flag was set as "Y/N" depending on availability. The query result was saved as parquet file and registered as table in the HIVE Thrift server, which was later read in visualized using Tableau.
It took a mere 10 seconds to run and process the summary report on a single node, 64GB RAM, 16 core processor. This will help the client management quickly identify the gap in demand and supply for specific product and if need be, take corrective action and also determine the total monetary amounts outstanding in backorders.