Climbing a mountain always looks like a big task, but it always begins with a first step and that deep breath of courage.
The human foot forward into the 21st century has ushered the big guns of globalisation and modernisation to severely impact every step taken. Numerous products, commodities, amenities and services are at our disposal making the desire to availability mapping incredibly robust.
Although there are irrelevant entrants that are misleading, disturbing and are miles away from the consumer preference that cloud the mapping scenario. A recommendation engine in the most naïve sense of the term is something that functions to predict the stepping stone of the mapping, the desire. According to definition a recommendation engine is an information filtering system that seeks to predict the preference that a consumer would have for a particular item.
In other words it is nothing but a set of algorithms which helps in predicting what among the given list of items would be likely preferred by the consumer. Most Internet users have come across a recommender system in one form or the other. Imagine, for instance, that a friend of yours recommends a new book, which subsequently makes you visit your favourite online bookstore. However after typing in the title of the book, it appears as just one of the results listed. Nonetheless a section of the web page possibly called “Customers Who Bought This Item Also Bought,” displays a list of additional books that can supposedly prove to be of interest to you. If you are a regular user of the same online bookstore, such a personalized list of recommendations will appear automatically on immediate entrance of the store’s webpage. The software system that determines which books should be shown to a particular visitor is a recommender system.
Recommendation engine not only makes your life easier by showing you the products in which you might be interested in but also helps to compare(based on various metrics) among the various products so that you can choose the best among them. In this era of smartphones, the decisions we take should be similarly smart and worthy. Efficient decision making can be made possible by enabling comparison of all the available options at a particular point of time. Recommendation can help in improving customer engagement, reduce churn and increase sales. Most of us are familiar with the cab services that can be availed through a single click of our smartphone. However sometimes when it gets difficult to find a cab, you switch amongst your apps trying to find one. Imagine, for instance, that you have a smartphone app that would show you all the cabs which are available in your nearby location at a particular point of time. Won’t this ease the situation at the consumers end? Let me list down some of the key metrics which a consumer thinks about before booking a cab.
- Duration or time the cab will take to reach customers location.
- Availability of cabs.
- Price per KM.
- Peak time Price or Surcharge Rate.
- Security while travelling.
With the recent abysmal Uber cab incident, the government has come up with certain regulations that would govern the cab business and is a crucial indicator of security determination at the time of travel. This, however alongside the customer reviews on Uber’s social media pages can serve as decision metric of security for a cab recommendation app that embodies all of the above on a single platform. In other words a sentiment analysis of the customer base regarding all of the required metrics can assist in truer predictions of customer desirables. Imagine if all of the above mentioned metrics can be made available on a single app, then how can our life become much easier? Let’s see:
- Suppose we open the app of a particular cab service (say uber). It took some time to load the map. Now after the map gets loaded, we see that there are no cabs available. Consequently we open the app of another cab service which again consumes time in order to load the map. In this process of app switch a lot of data alongside time is getting wasted. Had all the cab services been synchronized to a single app, we could have saved both of our time and data consumption.
- Being a rational individual, we always try to spend money wisely. Now suppose on opening an app of say Uber, you receive a notification that a surcharge rate of X amount would be applicable, which subsequently leads you to opening another app to see what price they are charging, in order to enable the comparison. Now again it would take some time to load every app. Had it been a single platform where one could see what is the prevailing surcharge rate or price, it would be beneficial for both time and data consumption.
The future of recommendation engines lies in integrating it with much needed customer experience enhancing features and functionalities. Some of the already successful examples of similar app structures are Jabong for consumer goods and accessories and Policy Bazaar for different insurance policies. With disruption taking center stage in practically every industry, intelligent recommendation engines will become the key differentiator for companies.
This blog is written by Rajani Rai, Aman Gupta and Soham Gangopadhyay from BRIDGEi2i
About BRIDGEi2i: BRIDGEi2i provides Business Analytics Solutions to enterprises globally, enabling them to achieve accelerated business impact harnessing the power of data. BRIDGEi2i’s Marketing Science solution brings in a unique combination of advanced analytics techniques and domain experience to help businesses develop a clear understanding of the market landscape, transform digital data into actionable insights and operationalize analytics to deliver incremental return on marketing investment. To know more visit www.bridgei2i.com