Summary
Overview
Work History
Education
Skills
Affiliations
Timeline
Generic

Jiaqi Guo

New York,NY

Summary

Master's student in Statistics at Columbia University with strong expertise in data analysis, machine learning, and predictive modeling. Proficient in Python (pandas, NumPy), SQL, and data visualization tools like Matplotlib and Seaborn. Experienced in leading projects focused on forecasting and performance optimization, including stock price prediction and sports performance analysis. Previous Data Analyst role involved optimizing production efficiency through data-driven insights, achieving a 10% improvement in workflow. Seeking to apply analytical and technical skills to drive data-informed decisions.

Overview

2
2
years of professional experience

Work History

Capstone Project Team Leader

Stock Price Prediction Using Deep Learning Models
Madison, Wisconsin
02.2024 - 05.2024
  • Compared the performance of Long Short-Term Memory (LSTM) and Transformer models in stock price forecasting, focusing on their strengths and weaknesses in short-term and long-term time series predictions. Employed TensorFlow and Keras to implement these models, using GPU acceleration to handle large datasets efficiently.
  • Leveraged Python's data manipulation libraries (pandas, NumPy) for data preprocessing, including normalization, sequence generation, and feature engineering, which improved the accuracy of the models by ensuring the data was optimally structured.
  • Employed Python libraries like Pandas for efficient data manipulation, and Matplotlib and Seaborn for sophisticated visual analytics, enhancing the interpretation of stock price trends and anomalies.

Undergraduate Research Assistant

University Of Wisconsin-madison
06.2023 - 11.2023
  • Led by Professor Karl Rohe's team, we analyzed over 50 medical research papers, applying advanced statistical techniques such as hypothesis testing, A/B testing, and multivariate analysis to detect biases in study designs, resulting in a 20% improvement in the accuracy of research conclusions.
  • Conducted in-depth assessments of AI models used in medical diagnostics, evaluating over 100 models across various domains (e.g., disease prediction, treatment efficacy) to ensure statistical validity. Improved model performance by fine-tuning algorithms and applying cross-validation techniques to reduce predictive errors by 15%.
  • Detected biases in machine learning methods commonly used in research papers, such as linear regression, decision trees, and neural networks, and proposed improvements to ensure more reliable and fair experimental outcomes.

Project Team Leader

SMT Data Challenge
Pittsburg
06.2023 - 08.2023
  • Engaged in a data challenge aimed at analyzing the performance of shortstops in baseball using advanced statistical methodologies, spatial statistics, and player interaction data. The challenge focused on evaluating the impact of positioning on defensive performance.
  • Conducted targeted filtering of datasets to identify successful defensive actions using Python's Pandas library. Executed detailed calculations of movement distances using NumPy to process numerical data efficiently. Developed custom functions to calculate lateral (X-axis) and longitudinal (Y-axis) movements from the positional data, which were tracked and analyzed to assess their impact on success rates.
  • Utilized Matplotlib and Seaborn for generating scatter plots and heatmaps, visualizing the correlation between movement patterns and defensive effectiveness, which provided a clear graphical representation of spatial performance metrics.

Data Analyst

Han's Laser Technology Industry Group Co., Ltd.
China
06.2022 - 08.2022
  • Data Querying and Management: Proficiently utilized SQL to extract, filter, and aggregate large datasets from the company's production database. Developed complex SQL queries to monitor key performance indicators (KPIs) such as machine utilization rates, production output, and defect rates, allowing for real-time tracking of production efficiency.
  • Production Data Analysis: Created a detailed pivot table for the Production Department, summarizing key statistical data from the first three quarters of 2022. The analysis identified bottlenecks in the production process, leading to a 10% improvement in workflow efficiency after the implementation of recommended changes.

Education

Master of Arts - Statistic

Columbia University in The City of New York
01-2026

Bachelor of Arts - Statistic

University of Wisconsin Madison
05-2024

Skills

  • Python, SQL, R, SAS, JavaScript
  • Algorithm R&D, Data Pipeline and Manipulation (Pandas, Numpy, Tidyverse, Spark, Hadoop)
  • Data Visualization (Tableau, PowerBI, Matplotlib, Seaborn, Plotly, ShinyR, GGplot2, Leaflet, Google Maps API)

Affiliations

  • Languages: Chinese(native); English (advanced).
  • Hobby: boxing, participated in the Wisconsin Madison Boxing Club since sophomore year. Photography, Enjoy capturing moments and landscapes, with a keen interest in developing my skills in photography.

Timeline

Capstone Project Team Leader

Stock Price Prediction Using Deep Learning Models
02.2024 - 05.2024

Undergraduate Research Assistant

University Of Wisconsin-madison
06.2023 - 11.2023

Project Team Leader

SMT Data Challenge
06.2023 - 08.2023

Data Analyst

Han's Laser Technology Industry Group Co., Ltd.
06.2022 - 08.2022

Master of Arts - Statistic

Columbia University in The City of New York

Bachelor of Arts - Statistic

University of Wisconsin Madison
Jiaqi Guo