## Inspiration

Our team was struck by the wealth disparity in America and wanted to share important financial tools with the public. People should not have to be rich to use a stock prediction tool. Many of these tools such as Bloomberg Terminals cost \$20000 to operate per year. We wanted to create a tool that would inform people on how a stock prediction model can be mathematically made, while not limiting the accuracy or functionality of the final product.

## What it does

The Monte Carlo simulation generates many paths that an individual’s stock portfolio can take based on the stocks’ history. Keeping the law of large numbers in mind, the average of all the paths is an accurate trendline of how the index should accumulate or lose wealth in the future. Additionally, this calculation is clearly explained on our website, thereby educating people that lack the knowledge of investing in the stock market as to how stochastic financial models work. Furthermore, our website is completely free of cost without any subscription fee.

## How we built it

Our team started out by deriving an iteration equation for the stochastic change between two points. After this was derived, team members focused on creating and defining variables pertinent to the random generation of hundreds of stock graphs over x amount of future days. Rate of change between two points, average rate of change, standard deviation, variance, and drift were all found from scratch instead of manipulating a data set with an API. We modeled the hundreds of stock permutations with Python, the NumPy library, and Pandas. The website we created to house our tool uses HTML. Flask is the communication between the Python back-end and the HTML front-end, enabling the user to input certain stocks and how many shares he or she has in said stock.

## Challenges we ran into

We ran into issues trying to interface our Python code with the website's HTML code. Interfacing was a concept that no team member was familiar with in the past and so more time was needed to complete the project's flask component.

## Accomplishments that we are proud of

We are surprised that we mathematically derived a working Monte Carlo Simulation that efficiently creates an accurate positive or negative trendline based on an index’s stock history in the time that we had. We're also proud that, as a freshman team, we were able to learn how to effectively implement python libraries and then integrate those python scripts with a website using flask.

## What we learned

We learned about how stochastic processes can be modeled. We learned to create a website and a corresponding web framework to handle Python code in HTML using flask.

## What's next for Project Lucreate

We want Project Lucreate to advise a user on what individual stocks are over-performing and under-performing. Additionally, it should be able to advise the user which stocks to invest in and which shares he or she could sell. We'd also like to improve financial education in the country and promote investing for the general masses.