Inspiration
We often find a consumer ranting about their newest purchase that they do not like or the forever apple fanboy who can't keep his mouth shut about the newest wireless charging that his iPhone X just came up with even though your two year old Galaxy S6 does the same thing. Many of these customer thoughts are released in the world of social media rather than amazon reviews or iMDb for movies. This meaningful thought sharing is not studied as robustly as it should be to gather feedback about products and industries. Therefore, we at MHacks trek through the treacherous terrain of social media, the place which trolls call home, to extract and identify meaningful transactional insights that are relevent to companies and consumers alike in order to build better products that are truly consumer oriented.
What it does
The finAnalyzer extracts meaningful transactional data from social media and performs social analytics to explore customer financial behaviour, categorizing them into major buckets, identifying potential clients with specifications that allow for the utilization of social media conversations and posts for proactive customer profiling to yield greater customer satisfaction. We also identify a list of satisfied and unsatisfied customers to improve company products and services. This analytics provides leverage to banks and company to expand their market and also keep track of their customer activies to help them grow further by creating targeted sales and marketting policies.
How we built it
We bulit it using python and twitterAPI to extract data and process the data to capture the trasactions from social media. Then using libraries we performed social analysis on these transaction to find solutions for the company.
Challenges we ran into
Firstly, capturing the transaction on social media. Then generating a workable data set that is clean with most of the noise. Dyanmic bucket to catagorize the transaction and generating solution which is identifying potential client in specific sector. Pro-active customer profiling was another challenge to help the companies workout the sales and marketing stratergies that improve company position in the market by working out with customer reviews on social media.
Accomplishments that we're proud of
Categorizing and genrating dynamic buckets and Pro-active customer profiling to improve companies' current market rating and build better customer client relationship.
What we learned
How to work with financial sector and data visualization and social analytics.
What's next for finAnalyzer
Machine learning to better capture the financial transaction on social media and NLP for better understanding the meaning of the conversation and post. Data collection from a greater variety of sources to calculate insigts that are true to a larger sample space.
Log in or sign up for Devpost to join the conversation.