still in active development
The restocking of Malaria commodities is currently done based on 6 month averages computed by MoH officials from the KHIS system data. These averages do not paint a clear picture of trends related to consumption such as seasonality, increases or decreases as well as other confounding factors.
We have decided to incorporate Prophet into our data analysis toolkit as a powerful forecasting tool. By leveraging Prophet's capabilities, we can effectively analyze the khis time-series data, and extract meaningful insights that can help us make informed decisions about the future. Prophet's ability to identify trends and seasonality in the data, as well as account for external factors such as holidays or events, allows us to create more accurate forecasts and predictions. This in turn allows us to make better decisions, optimize the strategies, and ultimately stay ahead in distribution. With Prophet at our disposal, we are confident that we can effectively understand the underlying patterns in the khis data and make data-driven decisions that lead to success.(prediction by default is a year at a time).
Why a chatbot? First and foremost, a chatbot can provide a more conversational and intuitive user experience for data analysis, compared to traditional UI's like dashboards or spreadsheets. With a chatbot, users can simply ask natural language questions and receive answers and insights in real-time, without the need to navigate complex menus or graphs.
| Features | Our analytic bot |
|---|---|
| Query response time | takes 0.022492s |
| Storage | in memory |
| Computational Power | less |
| Size | 39.1kb |
| Libraries | gensim |
| Efficiency | ✓ |
| Realtime | ✓ |
| Communication Protocol | uses Websockets |
Our new analytic bot offers a fresh approach to conversational AI(in data analysis and forecasting), with advanced natural language processing and a user-friendly interface. Our bot does not sacrifice speed at the expense of efficiency. Additionally, it offers real-time communication capabilities that greatly improve the user experience. It uses a topic modeling library instead of a deep learning library. This enables our bot to better understand and respond to user queries, while also reducing computational overhead and enabling more efficient use of system resources. With these advantages and many more, we believe our analytic bot will quickly become the preferred choice for anyone seeking a fast, efficient, and engaging conversational experience in trying to understand the KHIS data.