Yafi Arkan Hadaya loves programming, and analyze data. He has completed several projects on the Internet of Things, Data Science, Web Automation and Hardware Programming. For more info, check out his projects, and photos.
Yafi Arkan Hadaya loves programming, and analyze data. He has completed several projects on the Internet of Things, Data Science, Web Automation and Hardware Programming. For more info, check out his projects, and photos.
A manager at the bank is disturbed with more and more customers leaving their credit card services. They would really appreciate if there is a system that can predict customer who use other bank services for them, so the manager can proactively go to the customer to provide them better services and turn customers' decisions in the opposite direction.
Notebook ini berisikan Exploratory Data Analysis dan Modelling untuk memperdiksikan secara realistis apakah nasabah mengiyakan kampanye deposito melalui telemarketing.
Iowa Liquor companies need insight into their sales through data visualization. The data is placed in Google Big Query so it must be acquired using SQL.
At Shopee, we strive to ensure our customers' highest satisfaction for their shopping and delivery experience - fast and accurate delivery of goods. This can be better achieved if we have key address elements for each user address which allows us to accurately geocode it to obtain geographic coordinates to ship the parcel to our customers. These key address elements include Point of Interest (POI) Names and Street Names. However, most addresses that Shopee receives are unstructured and in free text format, not following a certain pattern. Thus it is important for us to develop a model to precisely extract the key address elements from it.
Frozen Dew is a natural phenomenon in the form of frost found in the Dieng, Central Java, Indonesia. Wind speed, temperature, and humidity factors in this. However, for rice fields, dew drops are detrimental to farmers. So that this IoT-based tool is used to monitor via cellphone and detect the presence of frostbite.
One of voice command recognition classifier is Reccurent Neural Network (RNN). RNN has several types, one of them is Long-Term Memory (LSTM). LSTM can recognize form sound signals which are sequential data or one-dimensional data. LSTM has a layer of memory to receive predictions of data learned, the forget gate to retrieve information that is not used so that it can make predictions more accurate in the future. In this study, several types of testing are done in testing single words and words in sentences. This study resulted in an average evaluation 97% for this two types of test.
Sensor Calibrator is a regression system that brings the measured value on the sensor closer to the calibrator value. In this study, the calibrator used was the thermogun. The results of this study are how robust the system using deep learning is compared to ordinary linear regression and how many error values are generated by the regression system using deep learning.
The problem is the company wants to make the right marketing strategy according to the conditions of its customer to creating customer segmentation so that credit card companies can create appropriate marketing strategies for each group of customers. What is the right customer segmentation based on available credit card customer information? In this project I use clustering method. The need to segment customers for marketing strategies.
Bob has started his own mobile company. He wants to give tough fight to big companies like Apple,Samsung etc. He does not know how to estimate price of mobiles his company creates. In this competitive mobile phone market you cannot simply assume things. To solve this problem he collects sales data of mobile phones of various companies. Bob wants to find out some relation between features of a mobile phone(eg:- RAM,Internal Memory etc) and its selling price. But he is not so good at Machine Learning. So he needs your help to solve this problem. In this problem have to predict a price range indicating how high the price is.
https://github.com/andikarachman/RNN-Twitter-Sentiment-Analysis has done a research about twitter analysis. And this research has improved the accuracy using stem and some data processing. From 81% to 95%. The conclusion is stemming and more data processing will give us a better result.
Collecting important files for Workforce Management needs, determine cable route plan for Workforce Management needs, and writing and calculating Bill of Quantity of projects that have been executed
Coordinating the procurement of equipment and project implementation, doordinating management division and technical division, programming IoT controller devices for sensors, communication devices, servers, sensor output monitoring, and device integrations, and routing electronics path
This is my Github Calendar and Activity.