NumPy Jobs

I am looking for an experienced AI/ML developer to build and evaluate machine learning models for a research-based project. Project Requirements: 1. Build and train machine learning models using Python. 2. Perform data preprocessing, feature engineering, and exploratory data analysis (EDA). 3. Implement and compare multiple models such as: * Logistic Regression * Random Forest * Support Vector Machine * XGBoost * Deep Learning models (CNN/LSTM if required) 4. Evaluate models using performance metrics such as: * Accuracy * Precision * Recall * F1-score * Confusion Matrix * ROC-AUC 5. Provide clear Python code using libraries such as: * NumPy * Pandas * Scikit-learn * TensorFlow or PyTorch * Matplotlib / Seaborn Deliverables: * Well-...

I have a raw Foodpanda dataset and want to understand how each restaurant truly performs. Your task is to run a focused exploratory data analysis that zeroes in on sales and revenue figures for every restaurant in the file. I’m interested in trends such as top- and bottom-line growth over time, seasonality, outliers, and any correlations you uncover between order volume, average basket size, discounts, or other revenue-related metrics you choose to engineer. Python, pandas, NumPy, and visualization libraries like Seaborn, Matplotlib, or Plotly are all welcome—as long as the code is clean, reproducible, and well-commented. Please avoid drifting into customer-review or delivery-time angles; the spotlight must stay on revenue-based performance. When you apply, attach a concise...

Sila Dafter atau Log masuk untuk melihat butiran.

I'm seeking a Python expert to develop a credit risk management model, focusing specifically on market data. Key Requirements: - Credit Risk Expertise: In-depth understanding of credit risk, particularly related to market data. - Python Proficiency: Advanced skills in Python for data analysis and modeling. - Data Handling: Experience in working with large datasets, especially market data. - Financial Acumen: Strong background in finance and risk management principles. Ideal Skills and Experience: - Proven experience in developing credit risk models. - Familiarity with relevant Python libraries (e.g., Pandas, NumPy, Scikit-learn). - Ability to provide clear documentation and insights on the model developed. Please share your relevant experience and approach to this project. I look ...

I’m working through an year long online course on Artificial Intelligence and Machine Learning and I’m running short on time for several graded assignments and mini-projects. Rather than general tutoring or technical platform troubleshooting, I specifically need someone who can step in, finish the required tasks, and submit clean, well-commented solutions on my behalf. This will be an ongoing project and will span an year. Typical exercises range from data preprocessing and feature engineering to training and evaluating models with libraries such as Python, NumPy, pandas, scikit-learn, TensorFlow or PyTorch. Code must run flawlessly in the course’s Jupyter-based environment and meet the rubric laid out in each brief (accuracy thresholds, narrative explanations, and any...

I have already trained and deployed a Logistic Regression model in Streamlit that classifies breast-tumour samples as malignant or benign. What I need now is a polished data-visualization layer so users can quickly grasp how each feature influences the prediction. My immediate focus is on bar-chart visualisations. I want clear, well-labelled bars that compare malignant vs. benign distributions, show feature importances, and surface any other insight you think adds value. The work should plug straight into my current Streamlit app and read from the same Pandas DataFrame I am already passing to the model. Although the main task is visualisation, I am also experimenting with feature selection, so if your code can be structured in a way that makes it easy to toggle feature subsets, that wi...

I need an 8- to 10-page conference paper that presents a hybrid machine-learning Security Information and Event Management (SIEM) framework combining Random Forest and Isolation Forest for network-threat detection. The manuscript must follow either Springer LNCS or Scopus proceedings guidelines, complete with the correct template, figure sizing, and reference style. Core structure • Introduction and literature review that positions the problem, surveys recent SIEM advances, and justifies the hybrid approach. • Methodology and data analysis describing data-preprocessing, feature engineering, model building in scikit-learn, and experimental evaluation on publicly available cybersecurity datasets (e.g., CIC-IDS 2017, UNSW-NB15, or similar). • Conclusion and future work...

I’m building a research-grade quantum simulator in Python and need a robust codebase that can accurately model multi-qubit circuits, apply standard gate operations, and return state-vector or density-matrix outputs. Whether you prefer to work directly with NumPy/SciPy or leverage existing open-source frameworks such as Qiskit, Cirq, or QuTiP is completely up to you; the key requirement is clean, well-documented code that runs reliably under Python 3.11. Please provide: • A modular simulation engine capable of handling at least 10-15 qubits, with optional noise or decoherence modelling • A clear, Pythonic API for defining circuits, executing simulations, and extracting results (probabilities, expectation values, etc.) • Unit tests plus a concise README that cover...

I have already deployed a full Streamlit application that predicts loan approvals in real time (live demo: , source: ). The pipeline currently includes Logistic Regression, K-Nearest Neighbors, and Naive Bayes models with standard scaling and the usual EDA-driven feature engineering. What I want now is a measurable lift in overall model performance, with the F1-score as the guiding metric. Feel free to explore more advanced algorithms (e.g., Gradient Boosting, XGBoost, LightGBM, calibrated ensembles, or even a tuned version of my existing classifiers) as long as they integrate cleanly with the existing Python | Pandas | NumPy | Scikit-learn stack and can be surfaced through the current Streamlit front-end. Key points you should address • Re-examine preprocessing and feature sele...

Our historical sales data is signalling shifts that we don’t fully understand yet, so the priority is a diagnostic analysis that tells us not just what changed, but why it changed. The raw tables cover order details, customer attributes, product SKUs and daily revenue going back three years. Primary questions on the table: • How have sales trends evolved month-to-month and season-to-season? • Which customer segments are driving (or dragging) revenue, and how has their purchasing behaviour shifted? • Which products or product groups are over- or under-performing once promotions, returns and stock-outs are factored in? A clean, reproducible workflow in SQL, Python (Pandas, NumPy, Sci-Py) or R is essential so the team can rerun the analysis after future data drops...

I need clean, well-commented Python code that lets me back-test a momentum-based, algorithmic trading strategy on Indian stocks through the Angel One smart-API. At a minimum, the script should: • Pull historical equity data with the Angel API endpoints I already use in live trading. • Let me set adjustable momentum parameters (look-back window, ranking criteria, rebalance frequency, position sizing) from a single config section. • Generate a fast vectorised back-test, calculate P&L, drawdown, Sharpe and basic trade metrics, then output them to a tidy DataFrame and a couple of matplotlib / seaborn charts. • Stay modular so I can swap the data-loader or plug the core logic into my live trading script later. Acceptance criteria 1. I run one command and th...