Machine learning is not a choice; it is an imperative: IBM

Machine learning is gaining popularity to deal with increasingly complex data and analysis problems. Many projections also point that the highest growth is in India IT spending in software and IT services for 2017. This includes building new digital platforms with Machine Learning at the center. IBM continues to be at the forefront of it all.

‘Machine Learning’ termed by an IBM decades ago has evolved significantly. Today, it enables enterprises to drive critical insights. Businesses are increasingly using machine learning to support advanced analytics across a growing range of industries and initiatives. With India’s focus on digitization, it’s an apt time for organizations to make this transition.

Prasanna Keny, Senior Technical Manager, IBM India says that going forward, machine learning is going to be an imperative and not a choice.“According to a Harvard study 72 percent of organisations are vulnerable to disruption due to digitization and data intelligence. For the respondents, 29 percent of organisations said they are extremely susceptible to market disruption while about 43 percent responded they are significantly susceptible due to the digital intelligence and machine learning used by their competitors. That is how important machine learning, analytics, deep learning or artificial intelligence has become in terms of competition and the ability for an organisation to maintain the leadership position,” said, Keny.

Citing various examples Keny explained the use cases of machine learning. He said it can be used for customer analytics and fraud combating.“A use case of analytics and machine learning is for countering fraud. When we think of fraud, the image that crops up in our mind is online payment fraud. But this can be used in a variety of cases. For instance, we have customers using it for expense fraud, procurement fraud or in case of insurance fraud detection for claims,” added Keny.

However, the whole process or the journey of machine learning involves challenges as well. Some of the challenges are data management where there is unavailability of prior data, the evolving environment and toll sets users, difficulties in collaboration where multiple people are working together and operationalizing.