This article will discuss an Agile practical approach to obtain a sustainable Innovation Platform.


The Construction Industry is required more than at any time previously to be constantly alert and adapt to change. Globalization, changing market conditions and client requirements, together with an era of opportunities created by the development of new technologies fuel a pressure to think out of the box.

Value delivery and client satisfaction are primary objectives of all construction companies. The innovation process in the construction industry is an important source of competitive advantage and value delivery. …

In Australia Open Tennis 2021, no more need for on-court judges anymore, Sensors and AI does the job on real time.

In the past, players had the chance to challenge the line judges decisions for a limited number of times during a game, Cameras monitoring the lines will replay and show if the ball was in or out. But in many cases, judges make wrong decisions and players run out of challenge attempts.

Research and innovations started from early 1970’s to electronic line judge, but now with the current advances in sensors, cameras and Artificial Intelligence (AI) algorithms, it became reality.

Dan Evans vs Karen Khachanov Dramatic match with horrible on-court lines judgements

Due to Covid-19 and to utilize the improvements…

How Kanban Board can help improving work management

Lean aims to minimize risk and waste while maximizing customer value. Lean is the foundation of Agile, which is a broader approach that focuses on continuous delivery and continuous improvement (Kaizen). Kanban is a lean tool that organizes work visually to meet lean objectives.

Kanban is a Japanese word meaning “Billboard”, it was invented by a Toyota engineer for Lean manufacturing in the late 1940s. …

Find out who of your employees is leaving the company and why

Employee turnover is expensive. Companies spend time, money and effort to train new employees to adapt to the new culture and work conditions. Those who resign take with them the experience, the training, and the culture. Newcomers need time to be able to manage existing products, to understand work procedures, learn about existing systems, culture, etc. It is suggested that 15.1% of the total U.S. workforce left their job in 2016.

Market Competition especially for highly skilled employees increases employees churn rate, so companies need to predict who might be quitting in order to attract her/him to stay!

SHRM predicts the annual turnover rate to be around 19%, and also assumes that the average cost-per-hire to fill a position is at $4,129. …

Lessons Learned and Recommendations

This article will highlight important recommendations and Lessons Learned that I have experienced in the past during the application of Nexus Scrum Framework, to succeed in applying the Change.

Agile life cycle

Scrum Team:

Scrum Team (ST) consists of Product Owner (PO), Scrum Master (SM) and Development Team (DT) which are maximum 9 for a 4 weeks Sprint.

  • Scrum team should follow the Scrum rules by book, it is being used everywhere else to make the process successful.
  • Scrum team should commit to time frame rules, i.e. if the Sprint time span is over, the sprint should stop.
  • ST may collaborate to resolve issues that…

How to make a story point estimate for an Agile Scrum user story, and how to measure Scrum Velocity

Story points is a measurement unit used to determine the complexity of user stories in the product backlog. Complexity means how big or small the job is, in terms of effort, resources, budget, dependencies and etc.

What is the Complexity of a User Story?

Story points are not a time estimate, they help the Scrum team measure the Velocity to achieve the business values. There are different types of scales used to create an estimate of user story point, among them:

  • Linear scale (1,2,3,4,5,6,7…)
  • Fibonacci sequence numbers (0.5, 1, 2, 3, 5, 8, 13 …)

I have chosen to use Fibonacci sequence because it is discrete and distance…

The crude oil price movements are subject to diverse influencing factors. Some of those factors are political and others related to inflation, economy, and etc. Would it be possible to predict future Oil prices based on historical data? This article will give an answer to this question.

Oil Mining, source: pixabay

During literature review of the subject, I was able to find a previous work by Chen et al. using deep learning to forecast WTI Crude Oil based on Long short-term memory LSTM.

Time Series

A time series is a sequence of records stored over regular time intervals.

Depending on the frequency of the interval, a…

Semantic Web aims to create a meaning and define inter-relationship for information available on the web

Semantic Web

In the early stages of the World Wide Web (web) it was necessary to develop standards to view web content (HTML language) and to create communication channels (N-Tier applications, email, ftp, etc.). As the web started to be the world’s largest knowledge base, accessible world wide, it became important to develop tools to transfer knowledge between cultures. However, it is still not possible for applications and agents to interoperate with other applications and agents without having a predefined, human created common framework of the…

Supervised machine learning predictions use training datasets to build Classification and Regression models, but those training datasets sometimes require enhancement. Imbalanced datasets need resampling, missing values needs resolving and categorical values should be converted to numbers.

This is not the Titanic but I liked the Illustration. Source: Pixabay

This article addresses null and categorical values treatment in a Data Science challenge Titanic: Machine Learning from Disaster challenge by Kaggle.

Categorical Variables

Categorical variable is a variable that may take one of a limited, and usually fixed number of possible values, such as Sex (Male/Female) OR Single (Yes/No) etc.

But machines don’t understand characters, every thing on the machine is a number, so we need…

Utilization of Markov Chain to re-sample minority in the data-set demonstrated promising results!

Example on Imbalanced Dataset: Grey apples are Majority while Red apple is minority

Imbalanced Corpus or Dataset was always a challenge for supervised machine learning fellows. Imbalance means that not all classes in the dataset has the same size, there could be a bias to one or more classes (majority) over other less presented classes (minority).

In a Sentiment Analysis challenge, the training dataset was imbalanced. The challenge aims to detect hate and abuse speech in tweets. The training dataset contains manually judged tweets with 0 for no hate or abuse and 1 otherwise. The training dataset is used then to predict the testing dataset tweets.

This is a full working example on…

Mustafa Abusalah

Expert in Information, Logic, Knowledge & Change

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