ResNet50 Transfer Learning with Grid Search Optimized Parameters for Covid-19 and Pneumonia Detection

Img from pixabay via link

In previous posts, we created several CNN networks for business problems ranging from fashion design, cancer detection, and animal detection etc. In this post, we will revisit the CNN topic. But instead of creating a model from scratch, we will use transfer learning and build the network on the top of a famous CNN architecture: ResNet50.

As normal, split into below:

  1. Context & Problem
  2. ResNet overview
  3. Data Review
  4. Train Model
  5. Takeaway

Let’s begin the journey 🏃‍♀️🏃‍♂️!

1. Context & Problem

AI and…


A Further Dig into Business Intelligence for Customer Marketing with Improved models

Img from pixabay via link

In a previous article, we created a stacked auto-encoder model for movie rating prediction. But as we know, with its encoder part, an auto-encoder model can also help with feature extraction. So, in this article, we will continue the journey on customer clustering using auto-encoder and k-means. As usual, it is split into 4 parts.

  1. Auto-encoder introduction
  2. Autoencoder modeling
  3. k-means modeling
  4. Takeaways

Let’s begin the journey 🏃‍♂️🏃‍♀️!

1. Autoencoder introduction

Autoencoders are a type of artificial neural network that is used to learn feature representation in an unsupervised manner. It uses the same data for input and output. As shown…


Business Intelligence for Marketing with k-means Clustering and PCA on Credit Card Dataset

Img from pixabay via link

In a previous post, we attempted to detect fraud in credit card transactions using various models. Here we will turn to another popular topic - Customer Clustering. This post aims to help friends in the marketing department. As usual, it is split into 5 parts.

  1. Problem statement
  2. Data Review
  3. Data processing
  4. k-means clustering
  5. Takeaways

Now let’s begin the journey 🏃‍♀️🏃‍♂️.

1. Problem statement

Marketing, as well known, is crucial for the growth and sustainability of any business. However, one of the key pain points for any marketing professionals is to know the customers and identify their needs. …


Creation and Evaluation of Handful of Machine Learning Models for Leave Prediction

Img from unsplash via link

In previous posts, I tried to predict if a bank customer is likely to leave, OR if an app user is likely to churn or subscribe. Here I will share recent work in the human resource domain to bring some predictive power to any firm struggling to retain their employees.

In this second post, I aim to evaluate and contrast the performances of a handful of different models. As always, it is split into:

1. Data Engineering

2. Data Processing

3. Model Creation & Evaluation

4. Takeaways

1. Data Engineering

Having completed a brief data exploration in the first post


Explanatory Data Analysis with Insightful Visualization and Interesting Findings

Img from pixabay via link

In previous posts, I tried to predict if a bank customer is likely to leave, OR if an app user is likely to churn or subscribe. Now I will share recent work in the human resource domain to bring some predictive power to any firm struggling to retain their employees.

In this first post, I will focus on exploring datasets for any interesting patterns. As always, it is split into below:

1. Problem Statement

2. Data Review

3. Distribution Analysis

4. Independent Variable Correlation Analysis

5. Response Variable Correlation Analysis

6. Takeaways

Let’s begin the journey 🏃‍♂️🏃‍♀️.

1. Problem Statement


A Guideline to Make the Best Use of FB Prophet for Time Series Forecasting

Img from unsplash via link

Time series prediction is one of the must-know techniques for any data scientist. Questions like predicting the weather, product sales, customer visit in the shopping center, or amount of inventory to maintain, etc - all about time series forecasting, making it a valuable addition to a data scientist’s skillsets.

In this article, I will introduce how to use Facebook Prophet to predict the crime rate in Chicago. Split into 5 parts:

1. Prophet Introduction

2. EDA

3. Data processing

4. Model prediction

5. Takeaways

Let’s begin the journey 🏃‍♀️🏃‍♂️.

1. Prophet Introduction

In 2017, Facebook Core Data Science Team open-sourced…


Machine Learning Models and Deep Neural Network Comparison and Sampling Techniques to Improve Performance

Img from Stockvault via link

In this article, let’s walk you through a Kaggle competition regarding credit card fraud detection. A deep neural network and two machine learning models will be built to tackle the challenge and compare different model performance. Additionally, data sampling techniques will be implemented to improve the model. As normal, split into 9 parts:

  1. Business challenge
  2. Data review
  3. Data processing
  4. DNN Model building
  5. DNN Model evaluation
  6. Decision Tree
  7. Random forest
  8. Sampling
  9. Summary

Now let’s begin the journey 🏃‍♂️🏃‍♀️.

1. Business challenge

Detecting fraud transactions is of great importance for any credit card company. We are tasked by a well-known company to…


Deep Dive into Common Machine Learning Models for Model Selection, Validation, and Optimization

Img from Pixabay via link

In this article, we will elaborate on ML model selection, validation, and optimization using online loan application data. What you will learn is how to create, evaluate, and optimize ML models. Specifically, we will focus on Logistic Regression, Support Vector Machine, and Random Forest. It is split into 7 parts.

  1. Business challenge
  2. Data review
  3. EDA
  4. Data processing
  5. Model building
  6. Model validation
  7. Parameter tuning
  8. Takeaways

Now, let’s begin the journey 🏃‍♀️🏃‍♂️.

1. Business challenge

We are tasked by a loan lending company to predict quality applicants. The job is to develop a model to predict the interest of applicants, by analyzing…


Deep Dive into Logistic Regression Modeling with Data Processing, Model Building, Validation, Feature Analysis, and Selection

Img from Pixabay via link

In the previous article, we created a logistic regression model to predict user enrollment using app behavior data. Hopefully, you had good learning there. This post aims to improve your model building skills with new techniques and tricks based on a larger mobile app behavior data. It is split into 7 parts.

1. Business challenge

2. Data processing

3. Model building

4. Model validation

5. Feature analysis

6. Feature selection

7. Conclusion

Now let’s begin the journey 🏃‍♀️🏃‍♂️.

  1. Business challenge

We are tasked by a Fintech firm to analyze mobile app behavior data to identify potential churn customers. The goal…


Deep Dive into EDA with Large Dirty Raw Data using Visualization and Correlation Analysis to Improve your Hands-on Skills

Img from Unsplash via link

In the previous article, we introduced how to perform EDA on a small app behavior dataset. Hopefully, you learned a lot there. This post aims to improve your EDA skills with a more complicated dataset and introduce new tricks. It is split into 6 parts.

1. Data review

2. Data cleaning

3. Numerical variable Distribution

4. Binary variable Distribution

5. Correlation analysis

6. Summary

Now, let’s begin the journey 🏃‍♂️🏃‍♀️.

  1. Data review

Quickly looking at the data shown in the below video, you can find there are 31 columns with 27,000 rows. …

Luke Sun

ML Enthusiast, Data Science, Python developer. Love to share articles about technology.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store