Business Solutions using Big Data
Data is the new oil. With the explosion of data in the 21st century, we see it being used as a decision
making tool to improve business processes across industries. Here are a few analytical solutions being
that used in various industries:
1) Logistics and Transportation Industry
i. Warehouse management – Identifying the best packaging solutions in shortest and most cost
effective time for every individual package.
ii. Delivery – Finding best possible routes for the delivery of packages using real time traffic data,
weather conditions. Providing ETA to customers. DHL analyzes 58 different parameters of
internal data to create a machine learning model for air freight. Maximize use of delivery staff
time and cost. Transmetrics is a predictive optimization company that helps cargo transport and
logistics service providers increase their operational efficiency by applying modern technology
such as artificial intelligence, data mining, predictive analytics and computer optimization.
Transmetrics SaaS (Software-as-a-Service) is offered in three steps: data cleansing, demand
forecasting, and predictive optimization.
iii. Routes developed using AI and Big Data can reduce fuel consumption cost in transportation.
iv. Optimize vehicles by demand. Reduce environmental impact along with cost. Improve Capacity
v. Complete optimization Supply chain management using analytics.
2) Traffic Management in the city
i. Use location services to manage traffic and signals. Track real time traffic and manage red light
signals in the city. In case of very high regular traffic, increase the green light sign for higher
time. Also, study possible infrastructure development that can lead to less traffic congestion.
ii. Predicting demand for public transport. Predicting demand for public/private transport at any given
time of the day. Forecasting requirements of vehicles on the basis of demand predicted
3) Banks, credit card application/payments, loan applications/payments etc.
i. Predicting whether an applicant is capable of repaying a loan. Use loan applications, declarations
and other user datasets. Comprehensive Credit Card approval process. Solving the problem of
NPAs. Using NLP, Image / Video processing, Learning from past data, Social life, online
activity, connections (build neural networks).
ii. Calculating Customer Lifetime Value using credit card information, banking transactional
iii. Fraud detection in Credit Card Payments/Bank loans. MasterCard integrated machine learning and
AI to track and process such variables as transaction size, location, time, device, and purchase data. The
system assesses account behavior in each operation and provides real-time judgment on whether a
transaction is fraudulent.
i. Refining recipes based upon user reviews.
ii. Food ordering demand forecasting and dynamic pricing for restaurants of SKUs.
iii. Estimating Calories from Food images.
5) Insurance Claims
i. Fake claims. Semantic analysis is a machine learning task that allows for analyzing both
structured, table-type data, and unstructured texts. The feature helps detect fake and falsified
claims in the insurance industry. For example, it improves car insurance claims processing.
Machine learning algorithms analyze files written by insurance agents, police, and clients,
searching for inconsistencies in provided evidence. There are many hidden clues in these textual
datasets. The rule-based engines don’t catch the suspicious correlations in textual data, and fraud
analysts can easily miss important evidence in boring investigation files. That’s why analyzing
claims is one of the most promising spheres for machine learning applications. A pre-research
analysis disclosed: Fraudulent claims are more likely not reported to police. Old vehicles are
more likely to be involved in fraud. Eighty percent of accidents that happen during holidays
involve fraud. Scams are more likely to involve third parties than legitimate claims.
6) Retail Shopping Industry
i. Creating Customer Life time Value
ii. Studying transactional data to create offers
iii. Studying products that are being bought together to create offers.
i. Finding the most appropriate value of a used car based upon parameters like age, kms run, brand,
engine capacity, etc.
i. Detect early stage life threating disease using historical results, advanced scientific research.
Suggest modifications by studying experts/scientist conclusion over the years in medical data in
order to delay creation of cancerous cells.
ii. Detecting and predicting chances of epidemic and suggesting ways to avoid or cure the same.
9) Government services
i. Emergency services like Ambulance, Fire Brigade, Police requirements. Detection of
requirement using satellite images, Real time traffic data/images, studying the impact of incident,
suggest actions to be taken and informing nearest service provider about the incident.
ii. Predict requirement of emergency calls and keep such facilities available as per prediction rather
than as per demand. Position ambulances and patrol vehicles in such a way that it’s easiest for
them to cover maximum area with minimum delay. Optimal routing of ambulance.
iii. Detecting violation of traffic rules using Image processing and charging it to their registration
iv. Identifying road conditions where most accidents happen and improving them along with similar
road where incidents might currently be low but may rise in near future.
i. Read text from the complete books and prepare a summary for every chapter in digital form
which can be printed into smaller books.
ii. Take surveys from ICSE and CBSE affiliated schools and professors. Run analytics on it and
provide a summary to each student a copy of best questions/ topics/ answers based on
suggestions from nation-wide qualified teachers.
i. Converting image into video. Predict what will happen in the form of a video by looking at
ii. Creating an image or video from the text. Read the text and convert what it wants into visuals.
Image or video. Similarly, give text from images or videos.
This a few findings of the projects that are currently happening in various industries. Also, a lot of such
projects are in research phase and hundreds of technology companies like datagarner are working on
finding business solutions in order to reduce human effort in redundant tasks and provide powerful