• This repository demonstrate proficiency in data science and machine learning techniques using a real-world data set and prepare a report for stakeholders.
• To demonstrate proficiency in data science and machine learning techniques using a real-world data set and prepare a report for stakeholders.
• Evaluate the results of machine learning models for predictive analysis, compare their strengths and weaknesses and identify the optimal model

The goal of this research is to analyze SpaceX Falcon 9 data collected through various sources and employ Machine Learning models to predict the success of first stage landing that provides other space agencies the ability to decide if they bid against SpaceX.

Following concepts and methods were used to collect and analyze data, build and evaluate machine learning models, and make predictions:

1. Collect data through API and Web scraping
2. Transform data through data wrangling
3. Conduct exploratory data analysis with SQL and data visuals
4. Build an interactive map with folium to analyze launch site proximity
5. Build a dashboard to analyze launch records interactively with Plotly Dash
6. Finally, build a predictive model to predict if the first stage of Falcon 9 will land successfully

This report will share results in various formats such as:

1. Data analysis results
2. Data visuals, interactive dashboards
3. Predictive model analysis results

• Recent successes in private space travel, space industry is becoming more mainstream and accessible to general population.
• Cost of launch continues to remain a key barrier for new competitors to enter the space race
• SpaceX with its first stage reuse capabilities offers a key advantage against its competitors.
• Each SpaceX launch costs around 62 million dollar and SpaceX can reuse stage 1 for future launches.
• This provides SpaceX a unique advantage where other competitors are spending around 165 mission plus for each launch.

• Determine if the first stage of SpaceX Falcon 9 will land successfully
• Impact of different parameters/variables on the landing outcomes (e.g., launch site, payload mass, booster version, etc.)
• Correlations between launch sites and success rates