Local Llama 2 Chatbot with LangChain, Pinecone, and Streamlit
This project aims to showcase the integration of technologies to build an intelligent and interactive chatbot that runs locally.
The main focus is to take advantage of the Llama 2 as open source Large Language Model developed by Meta AI.
While building with Llama 2, this project is intended to leverage its factual accuracy and consistency by providing it with reliable
and up-to-date information from the knowledge base. Achieving this involves the model with Pinecone as external database that could be used to store such novel information.
Lastly, we can establish the real environment using streamlit library as chatbot UI.
Traveloka Indonesia New Year Hotel Rooms
This project is dedicated to conducting a comprehensive analysis and comparison
of various aspects related to hotel accommodations offered during the New Year
holiday season in Indonesia, with a primary objective of providing invaluable insights into
the practices and improvements within the hospitality industry. In an increasingly
competitive market, the project seeks to contribute to the elevation of customer
satisfaction, highlighting trends, strengths, and areas for enhancement.
Statistical Analysis on USA Youtube Trending Videos
The project's specific focus is to generate valuable insights tailored for content
creators, marketers, and decision-makers, facilitating a deeper understanding of
YouTube user preferences and consumer behavior within the digital landscape. By
analyzing viewer engagement patterns and trending content topics,
this research aims to equip stakeholders with data-driven strategies to enhance their
online presence and effectively connect with their target audiences on the YouTube platform.
Customer Analysis on Olist E-Commerce
Olist have collected separated information data throughout the year. With current dataset,
it is hard to identify customer behaviour. However, the existing dataset poses a challenge
in comprehending customer behavior as it lacks a delineation of customer segments. The aspiration
of this project lies in empowering Olist to discern and classify their customers into meaningful
segments. This segmentation process will enable Olist to gain invaluable insights, refine their
marketing strategies, and provide personalized experiences, ultimately fostering enhanced customer
satisfaction and optimizing their business operations.
Predictive ML for Telco Customer Churn
In the telecom industry, marketing professionals place a strong emphasis on keeping customers from
switching to rival companies because it's much more cost-effective to retain existing customers than
to acquire new ones. Retention is a top priority, and a common strategy involves offering special
packages. However, this can be expensive if extended to all customers since only a small fraction
typically consider leaving, or "churning". To address this challenge, a predictive model will be
created to generate churn scores as indicators. These scores will help identify early signs of potential
churn, allowing the company to take proactive measures to prevent customers from actually unsubscribing.
