Contact usIndustry solutions
for data analytics
Explore uses of data in retail, banking, transport and manufacturing.
Explore solutions by industry
Retail
Plan your product assortment
Personalize product offers
Plan purchases and distribute stock across stores and warehouses
Forecast market conditions for new products
Improve loyalty programs
Track brand perception in the media and online
Choose locations for new stores
Monitor and improve product placement
Analyze in-store video to identify customer groups and shopping behavior
Plan staff shifts
Improve call center operations
Set up voice menus
Automate answers to common questions
Banking
Estimate customer lifetime value (LTV)
Segment customers
Recommend related products
Forecast demand by banking product and customer
Choose the next best offer for each customer
Estimate default risk for personal and business loans
Forecast ATM cash demand, capital needs and reserves
Identify links between customers
Choose locations for ATMs and branches
Identify customers at risk of leaving
Model how price changes affect demand and profit
Detect fraudulent transactions to trigger automatic card blocking
Schedule call center staff using forecasts of incoming calls
Transport
Predict equipment failures and plan preventive maintenance
Allocate resources based on current workloads
Plan routes and timetables
Choose vehicles suited to each route
Detect anomalies such as route deviations
Identify recurring causes of failures and delays
Forecast market conditions for new products and services
Personalize offers for customers
Forecast shipping volumes and plan purchases
Adjust prices as demand changes
Improve call center operations
Manufacturing
Reduce the use of costly raw materials while maintaining product quality
Adjust production settings in real time to reduce energy use without cutting output
Estimate process variables that are difficult or costly to measure directly
Spot defects early and adjust how materials are processed to reduce rejects
Tell us which problem you want to solve
info@ajtechfingroup.comWhat the pilot delivers
A business question for the pilot
A review of available data
Agreed evaluation criteria
A model tested against those criteria
A plan for deployment and support
Project results
75% average reduction in store inventory
Objective:
Reduce inventory while keeping products available in stores.
In 97% of observations, actual sales fell within the forecast range
Solution:
The model forecasts a range of weekly sales for each product in each store, up to a year ahead.
Tools: R, Python
Algorithms: XGBoost, CART, k-means
10% maximum difference
from the expert forecast
Objective:
Automate financial planning at head office by forecasting regional spending.
Over 120 cases of fraud
detected in the regions
Solution:
We integrated a tool built with KXEN and SAP BI into the client’s systems. It uses historical spending and regional economic indicators to forecast costs, detect fraud and adjust the budget.
Tools: R, KXEN, SAP BI
Algorithms: KXEN time-series algorithms
At least 9 subscriber segments for targeted campaigns
Objective:
Group customers for targeted campaigns and identify subscribers who also use competing providers.
86% accuracy in identifying subscribers who also used a competitor’s services
Solution:
The system groups subscribers and describes each segment. It estimates how likely each subscriber is to use another provider.
Tools: R, Python, Spark, Hadoop, Hive
Algorithms: XGBoost, CART, k-means, k-medoids, t-SNE
8 data sources connected
Objective:
Identify and prevent product losses and detect declines in the quality of petroleum products.
Over 1,000 incidents detected
Solution:
We connected the data sources to a Hadoop platform and set up processes to extract, transform and load the data. We built analysis modules and a web application for analysts.
Tools: Python, JavaScript, Shell, SQL, Hadoop, HDFS, Spark, YARN, Hive, Tez, Hue, ZooKeeper, Luigi, Kafka, NiFi, PostgreSQL, Microsoft SQL Server, Oracle, PI System, Django, AngularJS, Bootstrap, CSS, Docker, CentOS/RHEL
In over 80% of cases, the confirmed diagnosis was among the model’s top three predictions
Objective:
Help doctors assess possible diagnoses using readings from patient monitors.
98% probability that the condition the model considered least likely in the group was absent
Solution:
The model used readings from patient monitors to estimate the probability of each condition in a defined group and rank the possible diagnoses.
Tools: R
Algorithms: GBM, AdaBoost, k-means
How we deliver a model
1 Assess the data
Assess the available data
Define the project scope and success criteria
Agree on how to test the model
Obtain the data for the pilot
2 Run a pilot
Build the model
Test it under the agreed conditions
Compare the results with the success criteria
3 Deploy and monitor
Arrange regular data transfers or deploy the model in your environment
Compare versions of the service through A/B testing
Monitor forecast quality and update the model
Technologies we use
