Project 2

Investment Analytics Models

Project Overview

This project focused on using data analysis and automation to support investment decision-making. The goal was to organize financial data, compare investment options, and present insights in a clear format.

Problem

Investment analysis can involve repetitive calculations, assumptions, and comparisons. Without structure, it can be difficult to quickly identify which options carry higher risk or stronger potential return.

Tools Used

Excel
Python
pandas
Data visualization

Process

I created a simplified analytics workflow that compared investment options using risk level, expected return, and notes about uncertainty. The purpose was not to replace financial judgment, but to make the analysis easier to review and explain.

Code Artifact

			
import pandas as pd
investments = pd.DataFrame({
    "Investment Option": ["Option A", "Option B", "Option C"],
    "Risk Level": ["Low", "Medium", "High"],
    "Expected Return": [0.04, 0.07, 0.11],
    "Volatility Score": [2, 5, 8]
})
investments["Risk-Return Notes"] = investments.apply(
    lambda row: "Higher potential return with higher uncertainty"
    if row["Volatility Score"] >= 7
    else "Balanced option" if row["Volatility Score"] >= 4
    else "Stable but lower growth",
    axis=1
)
print(investments)

		

Output

Investment Option	Risk Level	Expected Return	Volatility Score	Risk-Return Notes
Option A	Low	4%	2	Stable but lower growth
Option B	Medium	7%	5	Balanced option
Option C	High	11%	8	Higher potential return with higher uncertainty

AI Artifact

I used AI to help organize the findings into a clearer summary for a non-technical audience. The AI helped convert raw analysis into plain-language insights, but I reviewed the final wording to make sure the conclusions did not overstate the data.

Human Review Decision

I kept human review as part of the workflow because investment assumptions need context. A higher expected return does not automatically mean a better option. Risk, uncertainty, and business goals must also be considered.

Key Takeaway

This project helped me practice turning data into decision support. It also reinforced that automation is useful for organizing and calculating information, but human judgment is still needed to interpret results responsibly.

Generative AI Role

How I Used Generative AI

During this project, I used generative AI as a support tool to help organize financial analysis, identify patterns in the data, and improve the clarity of my documentation. My goal was not to use AI to make investment decisions, but to help transform raw analytical findings into insights that could be communicated more effectively.

Prompt

“Review this investment analysis and suggest a clear way to present the findings. What trends, risks, and opportunities should be highlighted for a non-technical audience?”

AI Suggestion

The AI recommended organizing the analysis around risk, expected return, and key assumptions. It suggested summarizing findings in plain language, highlighting trade-offs between risk and reward, and presenting the results in a structured format that would be easier for stakeholders to understand.

What I Changed

I used the organizational structure suggested by the AI, but I revised the conclusions to ensure they accurately reflected the underlying data. I removed generalized recommendations that were not supported by the analysis and focused on presenting the results as decision-support information rather than investment advice.

Why Human Judgment Mattered

While the AI helped improve communication and presentation, it did not understand the full business context or the assumptions behind the data. I reviewed each suggestion, validated it against the project findings, and determined which insights were appropriate to include. Human judgment was necessary to ensure the final analysis remained accurate, balanced, and responsible.

Key Takeaway

This project reinforced my belief that AI can be valuable for organizing information and improving productivity, but it should not replace critical thinking. The most effective use of AI is as a tool that supports analysis while leaving final interpretation and decision-making to humans.