Reduce your e-commerce loses by analysing data, verifying users and detecting fraud orders.
Get a one month trial for free
No credit card info required!
The Indian e-commerce system is quite different from others especially in the ways it handles payments. One of the most common and sought after methods adopted by both the e-commerce companies and the customers is the Cash on Delivery method. In India COD makes up 70% of all Indian e-commerce.
While the COD method is seen as a customer-friendly way of doing transactions, e-commerce companies often pay a heavy price due to malpractices done with COD orders. The cash on delivery method also comes with a unique problem - Return to Origin (RTO).
Return To Origin (RTO)
RTO is when orders cannot be delivered and have to be shipped back to the warehouse. This puts a significant cost burden on e-commerce firms as they lose money on forward & reverse logistics.
Blocked inventory (stuck in transit)
Physical QC and re-packaging of items
Increased probability of damage item
Operations cost in processing this order
In case of COD orders, RTO can be as high as 40%. When one in three orders has the potential to damage your bottom line, instead of adding value to it, the situation is alarming.
Root Cause of RTOs
We analysed a number of COD related RTO orders and found some interesting, common patterns in them, like:
- Order without any real intent (Just for fun)
- Customer error (True intent but incomplete address)
- Price sensitive intent (The moment buyer finds a better price he reorders)
- Impulse buy but without paying (Knowing that there is no downside to refusing delivery)
- Intent to fraud (Habitual fraudsters)
Solutions using Machine Learning
Companies have tried experimenting with various rules to reduce RTO but these do more harm than good as many genuine orders are lost and customer relationships damaged. Solving the RTO problem by manually scanning every order does not work either due to the sheer scale of the problem and evolving nature of fraud techniques. With the Indian e-commerce market becoming hyper competitive, firms need better solutions as they cannot afford to lose customers and orders. Machine Learning technology offers an attractive solution as it addresses all the challenges in preventing fraud: scale, complexity and changing patterns.
Logisy is a platform that aims at reducing the losses e-commerce companies incur from RTO. Powered by big data and machine learning algorithms Logisy helps weed out orders that have a high probability of ending up in RTO situations.
Gathering digital evidences left behind users such as, Proxy IP, Device ID, Email addresses, Time to order etc and analysing them through machine learning models.
Using machine learning models to draw rich inferences from seemingly unrelated data, from validating real addresses to gathering various other information like phone models and their prices.
Using digital fingerprinting to trace and identify fraudsters who hide or erase traces of their previous frauds.
Following habitual fraudsters through the evidences and footprints they leave behind to ensure they are anonymously tracked and prevented from committing further frauds.
Automatically verifies addresses, phone numbers and PIN codes for errors. The Logisy algorithms also rates addresses to indicate chances of them being wrong.
Anonymously collects various user data to create unique user profiles and predict malicious user behaviors.
Tracks and analyzes users browsing behaviors on websites and apps and creates a machine learning driven predictive model that can flag and alert e-commerce companies of upcoming potential fraudulent activities.