Enterprises (SMEs and Start-ups ) in my town Nairobi are not making efficient use of the data they produce to understand their products and services. This not knowing customers can rarely lead to smart , data driven decision. The solution I saw was to come up with a inside sales CRM to provide tools to theunderserved community of salespeople who to help this Enterprises close more deals because I believe good customer experience build brand , loyalty , drive more sales and generate positive word-of-mouth.

What it does

The model Identifies the next best action for the customer through real-time insights that incorporate machine learning tools— sentiment analysis—can help Kafunge, an inside sales CRM for SMEs and Startu-up assess the likelihood of a deal closing or the level of a customer’s loyalty. I believe that Personally-tailored recommendations powered by machine learning can engage and delight customers with information and offers that are relevant to them

How I built it

The tech behind sentiment analysis involves natural language processing or linguistic algorithms that assign values to positive, negative or neutral text (converting opinions into datasets), while machine learning processes the datasets to reveal relevant trends over time. There’s significant planning required: How do you ensure the algorithms capture useful information? Are you identifying the right phrases to analyze? How can you convert findings into better products, services, and experiences?

Challenges I ran into

Slow internet connection to help in : Initialize a project using Pipenv Create a project skeleton Add the pre-trained model and create an interface to abstract the inference logic Update the request handler function to return predictions using the model Start the server and send a test request

Accomplishments that I'm proud of

Deployed a machine learning model for the first time

What I learned

docker and K8s, FastAPI, Patiences

What's next for kafunge AI

Integration with a Nodejs amd MongoDB to serve all the sales rep in my local area

Built With

  • bert
  • fastapi
  • huggingface
  • pytorch
  • transformers
Share this project: