IIT Kharagpur researchers create algorithm for marketing & sales on social media

Social media

Researchers at the Indian Institute of Technology Kharagpur (IITKgp) have developed an algorithm that tracks marketing and sales activities on social media. This low-cost solution would especially benefit micro, small and medium enterprises (MSMEs), according to the researchers. The solution is a model based on a computerised algorithm to identify social media influencers (with large contacts and followers) who have more reach and impact on social media.

The algorithm is applied to the data derived from select social media pages of test products. This is a great way to optimise marketing for companies with fewer resources, said professor MK Tiwari, who is leading the research at IIT Kharagpur.

“Such model would enable them to reach out to the right set of influencers at a lower cost and use their influence to increase sales and profit maximisation,” said Tiwari.

The algorithm was first tested on Facebook pages along with few other social media platforms. It used online retail products, with focus on fashion and apparel.

The IITKgp researchers will now take this up to the next level, which is commercialisation stage, by engaging with industry, especially MSMEs who typically use social media for selling their products through tech startups or IT companies.

The algorithm identifies social media influencers who could have more influence on potential buyers based on opinions and social ties on a popular social networking platform. In this research, the relation strength between influencers and adopters (potential customer) is considered to be the time difference between their comments.

“We already know that comments on social media affect potential buyers,” said Tiwari. “We have considered the personal valuation of the adopters based on their comments. Initially, we segregated the adopters and the influencers based on their valuation and the threshold value to become an influencer.”

In the second model, peers’ connections are considered to influence a user. The work has funded by the human resource development ministry under the scheme of centres for training and research in frontier areas of science and technology.