Seungkwon Lim

PERSONAL PROJECTS

Website

Own website using html

Sneaker Bot

Program that purchases limited sneakers

3D Phone Stand

Phone stand for my own phone

AutoCAD

AutoCAD Designs

ARCADE GAME

2D Arcade Game

under progress..

crypto trading bot

AI Assistant Program

Own AI Assistant using OpenAI API

On-Chain Whale Bot

Dectects on-chain whale activity and sends telegram alerts

Baccarat Simulator

Data was later used for trend analysis using Numpy

NASDAQ ML Predictor

Machine Learning Trading Model

Rolypolyy

Quantitative trading: Binance → Polymarket

Work Experience

Test Automation Intern | Ford Motor Company | Waterloo, ON | 2026.09 – 2026.12

As a Test Automation Intern at Ford, I convert vehicle requirements into automated hardware-in-the-loop tests for Ford’s AI in-vehicle voice assistant, covering media, radio, navigation, and climate, and I validate driver-distraction safety rules on the bench.

Converted Gherkin requirements into Python/Behave HIL tests for the voice assistant, raising media automation coverage from 52% to 100% and cutting runtime from 30+ minutes to about 1 minute.
Validated driver-distraction safety rules via CAN/CAN FD gear and speed simulation (VFS, ValueCAN) across Park, Drive, and Reverse, isolating 2 assistant logic defects (21 cases) from bench faults using VHAL signal evidence.
Restored stability testing on production Android builds by resolving a priority-zero defect, tracing silent assistant monitoring to Debug-log stripping via user vs. userdebug logcat, and shipping a drop-in Python fix that recovered 6/6 states.
Unblocked all Reverse-gear safety scenarios by enabling the rear camera via UDS (ISO 14229) security access and DID writes; root-caused a bench-wide audio failure to power-mode conflicts in 2 of 16 simulated ECUs.
Reported daily and weekly status to senior management at Ford’s U.S. headquarters; triaged and escalated 5 post-flash blockers on new builds, cutting resolution time by 67% (3 weeks to under 1 week).

Key Skills:

Python & Behave (BDD / Gherkin)
Hardware-in-the-Loop (HIL) Test Automation
CAN / CAN FD (VFS, ValueCAN)
UDS (ISO 14229) & Diagnostics
Android Automotive, adb & logcat
VHAL Signal Analysis & Defect Isolation
Driver-Distraction Safety Validation
Stakeholder Reporting & Issue Triage

Ford Motor Company Website

Work Experience

BMS Software Engineer | UW Evolution (Stellantis, U.S. Department of Energy) | Waterloo, ON | 2026.01 – 2026.04

As a BMS Software Engineer for the Battery Workforce Challenge, I designed, implemented, and verified a Battery Management System (BMS) in MATLAB Simulink. My work focused on State of Power (SOP) and State of Charge (SOC) management, grounded in the team's Software Requirements Document (SRD).

Compiled Year 3 BMS requirements from the SRD into granular, testable items for the Design Verification Plan and Report (DVP&R), adding traceability and explanation columns mapping each item to SRD sections and validation methods.
Updated the DVP&R template with ten low-level requirements (five SOP, five SOC), each linked to Model-in-the-Loop (MIL) test cases in Simulink Test Manager.
Built the BMS state machine from scratch in Stateflow with hierarchical structure: main sequential states (OFF, INIT, CONTACTOR_CONTROL, ACTIVE, FAULT_REACTION) and continuous background SOC/SOP calculations, with typed I/O, entry/during actions, and requirement-referenced transitions.
Developed ten structured CSV/Excel test case definition files covering charging permission, contactor/precharge behavior, crash response, CAN limit broadcast, current tapering, NVM SOC restoration, sensor accuracy, cell balancing, and full-charge detection (300 ms voltage hold).
Imported test cases via Test Harness and Test Manager using Signal Editor and Constant blocks; all ten MIL simulations passed with scope outputs confirming correct behavior (e.g., 30 A charge current only when parked and plugged in).
Architected a safety-critical MIL validation framework executing the DVP&R protocol across 20+ scenarios, increasing testing coverage by 40% and supporting zero-failure logic deployment.
Reduced computational latency by 15% using the MATLAB Profiler to refactor Stateflow logic and remove redundant transition overhead without sacrificing safety coverage.

Key Skills:

MATLAB / Simulink / Stateflow
Model-in-the-Loop (MIL) Testing & Simulink Test Manager
Battery Management System (BMS) — SOC & SOP
Design Verification Plan & Report (DVP&R)
Requirements Traceability (SRD → Test Cases)
Safety-Critical Embedded Software Verification
Test Harness Development & Signal Editor
Performance Profiling & Stateflow Optimization
Cross-Functional & Multi-University Collaboration
Technical Documentation & Structured Test Matrices

UW EVolution Website

Work Experience

Seoul Metropolitan Office of Education | Seoul | 2023.04.06 – 2025.01.03

I worked at the Seoul Metropolitan Office of Education as part of my military service where I actively collaborated with education officials(including the superintendent), government officials and internal teams, strengthening my communication and teamwork abilities. My responsibilities included:

Coordinating and supporting various education-related meetings, conferences, and official events.
Setting up and operating audio-visual equipment such as projectors, microphones, sound systems, lighting, and computers.
Ensuring optimal audio performance by preventing microphone feedback and managing frequency channels during press conferences.
Managing and maintaining CCTV systems and assisting in troubleshooting and repairing technical issues in collaboration with staff.
Monitoring vehicle access and providing support at the parking booth during the initial phase of service.

Key Skills:

Audio-Visual Equipment Management
Event Coordination & Logistics
Technical Troubleshooting & Problem Solving
CCTV Surveillance & System Support
Communication & Interpersonal Skills
Time Management & Attention to Detail
Stakeholder Collaboration
Public Service & Operational Support

Seoul Metropolitan Office of Education Website

Work Experience

MH Technologies Research Engineer Co-op | Incheon | 2021 05 10 – 2021 08 27.

I worked as a research engineer at MH Technologies. MH technologies is a company that provides solutions to thermal issues in the electric car industry. It is known for its Z-leak Tube technology which aims to cool the motor of electric cars.

My main job responsibility was to research various existing patents similar to the company's product and summarize or present the information. By doing so, I was able to grow my reserach ability significantly. I even suggested a new patent idea which was about cooling an axial flux motor. Researching was not limited to just patents and I also researched about different firms, thermodynamics, HVAC system, Taguchi Method and more.

Moreover, I was able to develop my communication and teamwork skills by assisting mechanical engineers do experiments and make samples of the company's products.

Company Website

Work Experience

Hotel Management Internship Loft Hotel | Seoul | 2020 04 – 2020 10.

I worked at Hotel Loft located in Seoul as an intern. I demonstrated strong communication skills by reaching out to hotel booking platforms regarding the hotel's features and listening to visitor’s complaints and feedback.

Using raw booking data provided by Loft Hotel’s management system, I conducted an end-to-end analysis in Jupyter Notebook with Pandas, NumPy, and Matplotlib. After cleaning and preprocessing the dataset (removing invalid rows, handling missing values, and engineering features such as group size), I performed data analysis including correlation heatmaps, cancellation trend analysis.

From this analysis, I discovered that bookings with more than three guests had cancellation rates about 10% higher compared to smaller parties. Additional insights showed that repeat guests canceled far less often, and bookings made 150+ days in advance were significantly more likely to be canceled.
Based on these findings, I recommended targeted promotions for parties of three or more (e.g., flexible cancellation policies or group discounts) and loyalty incentives for repeat customers. These data-driven suggestions could reduce cancellations, improve occupancy stability, and strengthen long-term customer retention

Moreover, I gained stronger teamwork skills by collaborating with hotel staff to fix and install electric devices such as CCTVs, laptops, and cleaning products. I displayed proficient critical thinking by researching and suggesting the implementation of a mounted automatic thermometer and a QR-code scanner to monitor potential visitors with COVID-19.

I also made efforts to attract new visitors by taking videos of the rooms, editing them, and uploading them to YouTube. (Link)

Company Website

About Me

Seungkwon Lim

I am a third-year Mechatronics Engineering student at the University of Waterloo (expected June 2029) with a strong interest in applying technical and analytical skills to solve complex challenges. I am currently a Test Automation Intern at Ford Motor Company, building hardware-in-the-loop tests for in-vehicle voice systems.

Outside of academics, I enjoy staying active through basketball and cycling, and I am passionate about financial markets, particularly algorithmic trading and cryptocurrency research. I aim to combine my engineering background with my interest in finance and technology to create impactful, innovative solutions.

NASDAQ100 Machine Learning Predictor

Project Overview

An advanced machine learning system for predicting daily NASDAQ US100 movements using sophisticated feature engineering, multiple model types, confidence-based filtering, and real-time signal generation. The system features trading logic, comprehensive backtesting with realistic condition, and potential integration for both historical analysis and live trading.

System Architecture & Workflow

Market Data & Feature Engineering

Retrieves up to ~10 years of historical data through MetaTrader 5 API
Builds 25+ engineered features capturing price action, volatility, trend, and patterns
Ensures data integrity with gap detection and missing-value handling
Organizes model outputs with consistent file naming for multi-symbol and multi-timeframe use

Model Training & Selection

Supports Random Forest, XGBoost, and LightGBM algorithms
Optional probability calibration via CalibratedClassifierCV
Uses time-series cross-validation for realistic evaluation
Automatically accounts for class imbalance (e.g., scale_pos_weight in XGBoost, balanced weights in Random Forest)
Optimizes confidence thresholds automatically (win-rate or PnL-based) for deployment

Advanced Feature Engineering

The system generates over 25 sophisticated features across multiple categories, each designed to capture different aspects of market behavior with enhanced robustness:

Enhanced Price Action & Candle Morphology

upper_wick_percent: Measures rejection at highs
lower_wick_percent: Captures support levels and buying interest
candle_range: Captures total movement (high–low) as a measure of volatility
gap: Opening price gap from previous close, measuring overnight sentiment

True Volatility & Risk Metrics

atr_14: True Average True Range using proper TR calculation
volatility_ratio: Current range relative to ATR-normalized volatility
range_change: Range expansion/contraction from previous session
vol_20: 20-period rolling volatility for adaptive threshold scaling

Multi-Timeframe Trend Analysis

ma_fast (5-period): Short-term trend direction and momentum
ma_slow (20-period): Intermediate trend confirmation
ema_200: Long-term trend bias and major support/resistance
trend_direction: Simple measure of short- vs. long-term moving averages, indicating overall trend bias.
above_ma_fast/ema_200: Binary indicators showing whether price is positioned above or below key moving averages.

Enhanced Momentum & Oscillators

rsi_14: Relative Strength Index (14-period), measuring momentum with smoothing
rsi_slope: Rate of change in RSI for momentum shift detection
macd: MACD main line using proper EMA calculation
macd_signal: MACD signal line for trend confirmation
macd_hist: MACD histogram showing momentum acceleration/deceleration

Breakout & Support/Resistance

prev_high/prev_low: Previous session's key levels for reference
breaks_prev_high: Binary flag for upside breakout confirmation
breaks_prev_low: Binary flag for downside breakdown confirmation

Advanced Candlestick Pattern Recognition

engulfing_bull/bear: Two-candle reversal patterns where the second candle fully engulfs the previous one.
confirmed_bullish_engulf: Bullish engulfing + uptrend + above EMA200
confirmed_bearish_engulf: Bearish engulfing + downtrend + below EMA200

Target Generation

Three target-labeling approaches are available, designed to adapt to varying market environments:

Standard Mode

Logic: Predicts the next bar’s direction based on price movement.

Label: Up if close[t+1] > close[t], otherwise Down.

Use Case: Provides broad market coverage with frequent trade opportunities.

Advantage: Maximizes data usage and captures all price shifts.

Strength: Ensures full alignment between backtest and live trading.

Fixed Threshold

Logic: A trade signal is only created if the next bar’s return is larger than a set threshold.

Labeling Rule:

1 (UP)

0 (DOWN)

Ignored

Use Case: Filters out small, noisy price moves.

Benefit: Focuses the model on significant movements, reducing false signals.

Adaptive Threshold

Logic: Dynamically adjusts entry thresholds based on market volatility.

Formula: Threshold = Base × (1 + 20 × Rolling Volatility).

Use Case: Maintains signal quality during both quiet and volatile markets.

Advantage: Reduces noise in low-volatility periods while capturing meaningful moves.

Feature Modes, Essentials Export & Threshold Selection

The system supports two feature modes for model training:

All Mode: Uses the complete engineered feature set (25+ features).
Essential Mode: Uses only the top-K most important features (default Top 10), automatically exported to suggested_essential_features.txt during backtests.

In addition, the backtest automatically optimizes the confidence threshold — the minimum probability required to generate a trade:

Win-Rate Mode: Selects the threshold that maximizes accuracy, subject to a minimum trade count for statistical reliability.
PnL Mode: Selects the threshold that yields the highest simulated profit and loss (using realistic execution costs).

This dual optimization ensures the chosen threshold balances signal quality and trade frequency, providing robust alignment between backtest performance and live deployment.

Interpreting Backtest Results

Backtest Visual Outputs

Running nasdaq_backtest.py not only saves CSVs and models, but also generates a range of visual performance analytics:

Equity Curve: Shows compounded account growth over time, reflecting win/loss streaks and drawdowns.
Confidence Sweep: Graphs how win-rate and trade count change as you vary the prediction threshold.
Calibration Curve (if enabled): Plots predicted probabilities vs actual outcomes for reliability analysis.
Feature Importance: Bar charts ranking which features had the highest impact on model predictions.
Return Distribution: Histogram of per-trade returns, useful for spotting outliers or fat-tail risks.

These visuals are saved alongside the CSV/model artifacts and provide a quick, intuitive way to understand the system’s strengths and weaknesses before deploying live.

Conducted Backtest Results

Train window: 2018-01-10 → 2023-12-15 · Test window: 2023-12-18 → 2025-09-03
Model: RandomForest · Mode: essential · Chosen Confidence > 0.58

Win Rate

64.29%

Based on 112 confident trades

Total PnL ($)

+228.21

Final Equity: $1,228.21

Max Drawdown ($)

-77.39

Peak-to-trough during test

Trades Taken

112

Confidence > 0.58

Prediction Balance

UP 70.8% / DOWN 29.2%

Across all predictions

Baseline Accuracy

54.15%

No confidence filter

With confidence > 0.58, the strategy achieved a 64.29% win rate over 112 trades, producing $228.21 total PnL (final equity $1,228.21) and a max drawdown of $77.39.
Essential Features Selected: rsi_14, rsi_slope, macd, candle_range, upper_wick_percent, atr_14, gap, macd_hist, lower_wick_percent, volatility_ratio

Backtest Artifacts

Saved model: US100Cash_16408_essential_randomforest.pkl
Confident trades CSV: US100Cash_16408_backtest.csv (112 trades @ thr=0.58)
Prob(UP) quantiles: [0.433, 0.490, 0.550, 0.6175, 0.6695]
Top 5 feature variances: macd, candle_range, atr_14, macd_hist, gap

Confidence sweep highlights: 0.58 → 112 trades @ 63.39%, 0.60 → 85 trades @ 64.71%, 0.62 → 64 trades @ 65.62%, 0.68 → 20 trades @ 75.00%.

Backtest Visual Outputs

Equity Curve: Compounded growth with drawdowns highlighted.
Confidence Sweep Plot: Win-rate vs. trades across thresholds (0.50–0.90).
Calibration Curve (if enabled): Probability reliability check.
Feature Importance: Tree-based importances (rsi_14, rsi_slope, macd, candle_range, atr_14, …).
Return Distribution: Per-trade PnL histogram for tail-risk insight.

Backtest Visualizations

Monthly PnL heatmap and feature importances

Practical Usage

The system can be used flexibly depending on your trading style. Here are the two most common setups:

End-of-Day (Daily) Prediction: Run main.py once at the close of the daily candle to forecast the next day’s direction. Best for swing/positional setups.
Intraday (5-Minute) Continuous Mode: Switch timeframe to M5 for rolling live signals. The system generates predictions at every bar close and can push them to a webhook_url for automated execution in futures or binary options trading.

Comprehensive Performance Analytics

Output File	Content	Purpose
`nasdaq_backtest_daily.csv`	Trade-by-trade results with equity curve	Detailed performance analysis and trade review
`{SYMBOL}_{N_BARS}_{FEATURE_MODE}_{MODEL}.pkl` e.g. `US100Cash_16408_all_randomforest.pkl`	Trained model + metadata (symbol, timeframe, features, model type encoded in filename)	Loaded in `main.py` for live trading via the `model_path` parameter
`suggested_essential_features.txt`	Top-K most important features	Feature reduction and model optimization

How to Use the System

Run Backtest: Execute nasdaq_backtest.py to generate performance metrics, equity curves, and suggested essential features.
Review Outputs:
- Check nasdaq_backtest_daily.csv for trade-by-trade results.
- Review suggested_essential_features.txt for the recommended feature set.
- Note the trained model file {SYMBOL}_{N_BARS}_{FEATURE_MODE}_{MODEL}.pkl.
Configure Live Trading: Update main.py with:
- Your chosen feature_mode (e.g., "essential" or "all") and the threshold
- The confidence threshold found during the sweep (balances win-rate and trade frequency).
- The trained model file path (model_path → e.g., "US100Cash_16408_all_randomforest.pkl").
Run Live Mode: Start main.py to generate signals (single-shot or continuous daily operation).
Monitor & Retrain: Periodically re-run backtests to recalibrate thresholds, update feature sets, and refresh the trained .pkl file as markets evolve.

Example: Using the Trained Model in main.py

# main.py (excerpt)
model = NASDAQTradingModel(
    model_path="US100Cash_16408_all_randomforest.pkl",  # from backtest
    symbol="US100cash",
    timeframe=mt5.TIMEFRAME_D1,
    feature_mode="all",
    model_type="randomforest",
    confidence_threshold=0.60,
    # ... other params
)
# The .pkl file is loaded and used for real-time predictions

PERSONAL PROJECTS

Work Experience

Test Automation Intern | Ford Motor Company | Waterloo, ON | 2026.09 – 2026.12

Work Experience

BMS Software Engineer | UW Evolution (Stellantis, U.S. Department of Energy) | Waterloo, ON | 2026.01 – 2026.04

Work Experience

Seoul Metropolitan Office of Education | Seoul | 2023.04.06 – 2025.01.03

Work Experience

MH Technologies Research Engineer Co-op | Incheon | 2021 05 10 – 2021 08 27.

Work Experience

Hotel Management Internship Loft Hotel | Seoul | 2020 04 – 2020 10.

About Me

Seungkwon Lim

Enhanced Price Action & Candle Morphology

True Volatility & Risk Metrics

Multi-Timeframe Trend Analysis

Enhanced Momentum & Oscillators

Breakout & Support/Resistance

Advanced Candlestick Pattern Recognition

Standard Mode

Fixed Threshold

Adaptive Threshold

Example: Using the Trained Model in main.py

Core Libraries

Visualization & Utilities