dwiputris Goto Github PK

data_pre-processing_credit_scoring

In this project data pre-processing is employed to handle a dataset that is peppered with problems, like missing values, explicit duplicates, implicit duplicates, and numerous categories.

dwiputris

Config files for my GitHub profile.

eda_video_games

Exploratory Data Analysis is applied to analyse past data of video games that are sold during year 1980 to 2016. The purpose of the analysis it to find out which games, platforms, genres, and ESRB rating class that highly marketable in year 2017.

exploratory_data_analysis_car_advertisement

In this project, Exploratory Data Analysis approach is applied to analyse a dataset of car advertisement in a web, to determine what factors correlate with a car's selling price.

html-sample-with-style-in-css

a sample of web development in html, with style in a separate css file

hypothesis_testing_taxi_ridings

Cab riding trips are analyzed to understand more on how trips are affected by weather condition, how certain spots attract more taxi passengers, and how a taxi company stands out in making most trips.

machine-learning-anticipating-churn-telecom

With imbalanced observed data, a search for the best model is conducted. The telecommunications operator named Interconnect wants to predict the churn rate of their clients. If it is known that a client plans to terminate their service, they will be offered promotional codes and special package options.

machine-learning-anticipating-churns-a-case-of-imbalanced-data

With imbalanced observed data, a search for the best model is conducted. The bank is seeing its customers leave. Wondering if there are patterns to their decision to exit, the bank wishes to anticipate for this trend. When the positive class is the minority in an imbalanced dataset, a model need to be trained for robustness.

machine-learning-with-business-metrics

my_first_machine_learning

In this project, the best model is searched to predict a subscription plan for a telco's customers.

project_airbnb

Airbnb listings near Zaanse Schans, Amsterdam with budget below IDR 2,000,000

project_airbnb_more

statistical_data_analysis_telco_revenue

In this project, statistical analysis approach is employed to decide what hypothesis to be rejected. Scipy Stat library is used to find the pvalue that will determine if Hypothesis Null should or should not be rejected.

time-series-taxi-orders