You will get I will build a Machine Learning forecasting model in Python
Project details
I build production-ready Machine Learning models that turn your
raw data into accurate, interpretable predictions.
With a Master's degree and hands-on experience in time series
forecasting and classification, I deliver models that work on
real-world data — not just clean textbook examples.
Recent project: Polypropylene price forecasting using XGBoost
with Walk-Forward validation. Results on unseen test data:
• R² = 0.80
• MAE = 178 CNY/ton (2.3% average error)
• 87.5% coverage inside 95% confidence interval
• Deployed as interactive Streamlit dashboard
What makes my work different:
✔ No data leakage — proper train/test methodology
✔ Confidence intervals on every prediction
✔ Feature engineering from raw variables
✔ Hyperparameter tuning with Optuna
✔ Clean, documented, reusable Python code
✔ Streamlit dashboard in Advanced tier
I work with any structured dataset — financial data, commodity
prices, sales forecasting, demand planning, or any numerical
prediction problem.
Send me your dataset and prediction goal and I will tell you
honestly what accuracy is achievable.
raw data into accurate, interpretable predictions.
With a Master's degree and hands-on experience in time series
forecasting and classification, I deliver models that work on
real-world data — not just clean textbook examples.
Recent project: Polypropylene price forecasting using XGBoost
with Walk-Forward validation. Results on unseen test data:
• R² = 0.80
• MAE = 178 CNY/ton (2.3% average error)
• 87.5% coverage inside 95% confidence interval
• Deployed as interactive Streamlit dashboard
What makes my work different:
✔ No data leakage — proper train/test methodology
✔ Confidence intervals on every prediction
✔ Feature engineering from raw variables
✔ Hyperparameter tuning with Optuna
✔ Clean, documented, reusable Python code
✔ Streamlit dashboard in Advanced tier
I work with any structured dataset — financial data, commodity
prices, sales forecasting, demand planning, or any numerical
prediction problem.
Send me your dataset and prediction goal and I will tell you
honestly what accuracy is achievable.
Machine Learning Tools
scikit-learn, XGBoostWhat's included
| Service Tiers |
Starter
$50
|
Standard
$120
|
Advanced
$250
|
|---|---|---|---|
| Delivery Time | 5 days | 7 days | 14 days |
Number of Revisions | 1 | 2 | 3 |
Number of Model Variations | 1 | 2 | 3 |
Number of Scenarios | 1 | 2 | 3 |
Number of Graphs/Charts | 2 | 3 | 9 |
Model Validation/Testing | |||
Model Documentation | - | ||
Data Source Connectivity | - | - | |
Source Code |
Optional add-ons
You can add these on the next page.
Additional Revision
+$20
Streamlit dashboard
(+ 2 Days)
+$80
Extra data source
(+ 2 Days)
+$30
Video explanation
(+ 1 Day)
+$25Frequently asked questions
About Ouais
Machine Learning Engineer | Time Series Forecasting | Python | XGBoost
El Oued, Algeria - 12:07 pm local time
experience building end-to-end ML solutions — from raw data to deployed
applications.
My recent work includes:
▸ Commodity Price Forecasting — Built a Walk-Forward XGBoost model to
predict Polypropylene futures prices using 7 market indicators
(oil, gas, USD/CNY, LLDPE, BDI, naphtha, copper). Achieved R²=0.80
and 2.3% MAPE on unseen test data. Deployed as an interactive
Streamlit dashboard with 95% confidence intervals.
▸ Classification Projects — Applied supervised learning models
(Random Forest, XGBoost, Logistic Regression) with hyperparameter
tuning and cross-validation.
What I bring to every project:
✔ Clean, well-documented Python code
✔ Proper train/test methodology — no data leakage
✔ Feature engineering from raw data
✔ Model explainability (feature importance, SHAP)
✔ Deployment-ready deliverables (Streamlit, API, notebook)
I work best on problems involving structured/tabular data, time series,
financial data, and predictive analytics.
Let's discuss your project.
Steps for completing your project
After purchasing the project, send requirements so Ouais can start the project.
Delivery time starts when Ouais receives requirements from you.
Ouais works on your project following the steps below.
Revisions may occur after the delivery date.
Data Review & Understanding
Analyze your dataset, check quality, identify missing values, and confirm the prediction target and features.
Feature Engineering
Create lag features, rolling averages, and derived variables to give the model maximum predictive signal.