Embedded Files
Binyam Sisay
Highlights
Highlights
Currently working on..
Causal inference refers to an intellectual discipline that considers the assumptions, study designs, and estimation strategies that allow researchers to draw causal conclusions based on data.
This project aims to forecast sales in all their stores across several cities six weeks ahead of time. It is identified that factors such as promotions, competition, school and state holidays, seasonality, and locality as necessary for predicting the sales across the various stores. Previously recorded data was provided and future sales predictions are made using that data.
It makes use of Tensorflow for modeling building and SKlearn for pipelines. The project demonstrates an Exploratory data analysis of customer purchase is " Rossmann Pharmaceuticals " company.
Approach:
Approach:
Exploring the data and Data Pre-processing
Building models with sklearn pipelines
Choose a loss function
Post Prediction analysis using Rebs
USER ANALYTICS - TELECOM INDUSTRY
USER ANALYTICS - TELECOM INDUSTRY
Client investigation on the client outline utilization of the Telecom item, client commitment, experience, and fulfillment examination. The principle objective of the undertaking is to dissect openings for development and recognize freedoms to drive benefit by changing the focal point of which items or administrations are being advertised.
The key skill acquired is data visualization using seaborn and matplotlib in python.
APPROACH
UnComprehend the dataset, distinguish the missing qualities and exceptions if any utilizing visual and quantitative strategies to get a feeling of the story it tells
Recognizing the main 10 handsets utilized by the clients. Then, at that point, recognizing the main 3 handset makers Next, distinguish the best 5 handsets for each best 3 handset producer.
Collecting per client the data in the segment number of xDR meetings Session length the absolute download (DL) and transfer (UL) information and by the complete information volume (in Bytes) during this meeting for every application
Analyze the data using Univariate, Bivariate, and Multivariate analysis. Use a Correlation Analysis and Later analyze user engagement.
Classify the data using k-means clustering algorithm
Further analysis on user experience and satisfaction analysis.
Page updated
Google Sites
Report abuse