Xinyao Wu Blog

LLM Science Exam

A ML pipeline for building a Large Language Model

# This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python # For example, here's ...

Posted by Xinyao Wu on July 22, 2023

Identifying age related conditions

Utilized

# This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python # For example, here's se...

Posted by Xinyao Wu on July 22, 2023

The Evolution of Data Storage

Data Warehousing, Data Lake, and Data Lakehouse

Mind map of this article Introduction This article is inspired by a post written by a Databricks engineer. It is aimed at company engineers who use the Databricks ecosystem but are unclear about ...

Posted by Xinyao Wu on July 17, 2023

Unleashing the Power of LLMs

Revolutionizing Natural Language with Advanced AI Models

What is an LLM? A Large Language Model (LLM) refers to a type of artificial intelligence model designed to understand and generate human-like text. These models are trained on vast amounts of text ...

Posted by Xinyao Wu on July 9, 2023

Twitter Hateful Comments Detection

Utilized NLP, Bi-Directional LSTM to detect hateful comments to maintain Twitter environment.

Goal: Use TPUs to identify toxicity comments across multiple languages. import numpy as np import pandas as pd from tqdm import tqdm from sklearn.model_selection import train_test_split import ten...

Posted by Xinyao Wu on July 22, 2021

Identify Fraudulent Activities

Use Random Forest to detect fraudulent activities for E-commerce websites.

Goal Build a machine learning model that predicts the probability that the first transaction of a new user is fraudulent. import numpy as np import pandas as pd import seaborn as sns import matplo...

Posted by Xinyao Wu on April 28, 2021

Credit Card Fraud Detection

Use K-Means clustering to detect irregular credit card transaction.

Goal: Identify unusual/weird events that have a high chance of being a fraud with credit card transactions. import pandas as pd import numpy as np from sklearn.cluster import KMeans 1: Customer...

Posted by Xinyao Wu on June 22, 2020

Funds Inflow Prediction (2014) for Ants Financial Services Group(AFSG)

Use ARIMA, STL to find the inflow finding trend for AFSG.

Goal: Predict the trend of Funds Inflow using historical time series data. import matplotlib.pyplot as plt import pandas as pd import numpy as np import statsmodels.api as sm from statsmodels.tsa....

Posted by Xinyao Wu on March 21, 2019