Upload home.py

apps/home.py

@@ -6,7 +6,20 @@ def app():
     st.title("Ghana - Understanding The Disconnect between Skills and Jobs")
     
     st.markdown('''
-    In Africa, there is often a disconnection between the skills that job seekers possess and the skills that employers require. This can be due to a lack of access to education and training opportunities, as well as a lack of alignment between the education system and the needs of the job market.
- Additionally, many employers in Africa may not have the resources or capacity to provide the necessary training and development for their employees. As a result, there is often a mismatch between the skills that workers have and the skills that employers need, which can make it difficult for workers to find employment or for employers to find qualified candidates.
-    ''')
+    Using Ghana as a case study, the project aims to discover why there is a mismatch between job opportunities and available skills. This mismatch could be caused by limited access to education and training, a lack of alignment between the education system and the needs of the job market, and a need for more resources for employers to provide training and development for their employees. To better understand this skill gap issue, this user-friendly deep learning-based NLP tool will make it easier to measure the gap between the skills and qualifications of applicants, educational or training programs, and the requirements of the job market. The team working on this project consists of experts from various continents, and the tool is currently only developed for the Ghana ecosystem.
+
+    - **Ethical Statement of the Project**
+
+1. The datasets utilized were publicly available from various Ghanaian jobs and resume websites.
+2. The dataset does not contain personal information, and they are easily accessible in the project management folder, which will be provided upon request.
+3. The research commits to responsible and sustainable innovation and considers ethical guidelines for the outcomes and technologies.
+4. The project promotes collaboration, respect, and fairness among team members, fostering inclusive practices and recognizing diverse perspectives.
+ 
+    - **Behavioral Analysis of the Model [Human Evaluation and Report]**
+
+We employed 15000 samples of data from 21 distinct types of job categories to train the model. 
+Model Limitation: One of the main limitations of the model is the dataset it was trained on. The original dataset had 62 categories, but due to insufficient data in many categories, some of them were combined, resulting in 21 categories. This approach of combining categories can make accurate CV segmentation more difficult. Additionally, the model was trained on an unbalanced dataset, which may lead to bias in certain situations. To overcome this limitation, larger and balanced datasets for each category would allow for more precise CV segmentation and lead to better output.
+
+The model is scalable for other countries; however, country-specific data will be required to retrain the model.
+          ''')