Authors:
(1) Mark Potanin, a Corresponding (authorpotanin.m.st@gmail.com);
(2) Andrey Chertok, (a.v.chertok@gmail.com);
(3) Konstantin Zorin, (berzqwer@gmail.com);
(4) Cyril Shtabtsovsky, (cyril@aloniq.com). Table of Links Abstract and 1. Introduction 2 Related works 3 Dataset Overview, Preprocessing, and Features 3.1 Successful Companies Dataset and 3.2 Unsuccessful Companies Dataset 3.3 Features 4 Model Training, Evaluation, and Portfolio Simulation and 4.1 Backtest 4.2 Backtest settings 4.3 Results 4.4 Capital Growth 5 Other approaches 5.1 Investors ranking model 5.2 Founders ranking model and 5.3 Unicorn recommendation model 6 Conclusion 7 Further Research, References and Appendix 4.2 Backtest settings In this study, several experiments were conducted with different backtest configurations, we called them earlybird and any. The earlybird configuration exclusively permits entry for companies only in rounds B or C, while the any configuration broadens the entry criteria to any round within the list of series_b,series_c,series_d,series_e,series_f, series_g,series_h,series_j,series_i, as long as they are within the considered backtest window. The choice of entry configuration depends on the stage at which we enter the company. Similarly, the choice of exit configuration depends on when we decide to exit the company based on its success event (IPO/ACQ/unicorn), as discussed in Section 2.2. However, since the "unicorn" status can occur in the early rounds, there is a question of which round to exit. Two approaches were considered: using first approach we exit the company when the first success event occurs, while using last approach we exit on the last success event, analogous to "we sit until the end." The main approach used in this study is the earlybird_last due to business requirements. However, this approach has its drawbacks, such as the fact that the company success flag becomes known later in time, resulting in a smaller dataset size for training at the beginning of the backtest and a slightly lower quality of the backtest compared to the earlybird_first approach. This paper is available on arxiv under CC 4.0 license. Authors: (1) Mark Potanin, a Corresponding (authorpotanin.m.st@gmail.com); (2) Andrey Chertok, (a.v.chertok@gmail.com); (3) Konstantin Zorin, (berzqwer@gmail.com); (4) Cyril Shtabtsovsky, (cyril@aloniq.com). Authors: Authors: (1) Mark Potanin, a Corresponding (authorpotanin.m.st@gmail.com); (2) Andrey Chertok, (a.v.chertok@gmail.com); (3) Konstantin Zorin, (berzqwer@gmail.com); (4) Cyril Shtabtsovsky, (cyril@aloniq.com). Table of Links Abstract and 1. Introduction Abstract and 1. Introduction 2 Related works 2 Related works 3 Dataset Overview, Preprocessing, and Features 3 Dataset Overview, Preprocessing, and Features 3.1 Successful Companies Dataset and 3.2 Unsuccessful Companies Dataset 3.1 Successful Companies Dataset and 3.2 Unsuccessful Companies Dataset 3.3 Features 3.3 Features 4 Model Training, Evaluation, and Portfolio Simulation and 4.1 Backtest 4 Model Training, Evaluation, and Portfolio Simulation and 4.1 Backtest 4.2 Backtest settings 4.2 Backtest settings 4.3 Results 4.3 Results 4.4 Capital Growth 4.4 Capital Growth 5 Other approaches 5.1 Investors ranking model 5.1 Investors ranking model 5.2 Founders ranking model and 5.3 Unicorn recommendation model 5.2 Founders ranking model and 5.3 Unicorn recommendation model 6 Conclusion 6 Conclusion 7 Further Research, References and Appendix 7 Further Research, References and Appendix 4.2 Backtest settings In this study, several experiments were conducted with different backtest configurations, we called them earlybird and any. The earlybird configuration exclusively permits entry for companies only in rounds B or C, while the any configuration broadens the entry criteria to any round within the list of series_b,series_c,series_d,series_e,series_f, series_g,series_h,series_j,series_i , as long as they are within the considered backtest window. earlybird series_b,series_c,series_d,series_e,series_f, series_g,series_h,series_j,series_i The choice of entry configuration depends on the stage at which we enter the company. Similarly, the choice of exit configuration depends on when we decide to exit the company based on its success event (IPO/ACQ/unicorn), as discussed in Section 2.2. However, since the "unicorn" status can occur in the early rounds, there is a question of which round to exit. Two approaches were considered: using first approach we exit the company when the first success event occurs, while using last approach we exit on the last success event, analogous to "we sit until the end." first last The main approach used in this study is the earlybird_last due to business requirements. However, this approach has its drawbacks, such as the fact that the company success flag becomes known later in time, resulting in a smaller dataset size for training at the beginning of the backtest and a slightly lower quality of the backtest compared to the earlybird_first approach. earlybird_last earlybird_first This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

Insights from Backtest Results on Startup Investment Strategies

Evaluating Startup Predictions with Backtesting and Portfolio Simulation

Read My Stories

Too Long; Didn't Read

Boost your HackerNoon story @ $159.99! 🚀

Earlybird vs. Any in Startup Investment Models

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

A Comprehensive Analysis of Startup Predictive Models

Startup Success Prediction and VC Portfolio Simulation Using CrunchBase Data

How Machine Learning Is Changing Startup Predictions

How We Used Crunchbase Data to Predict Startup Success

Unicorns vs Failures: Constructing Comprehensive Datasets for Predictive Modeling

A Comprehensive Analysis of Startup Predictive Models

Startup Success Prediction and VC Portfolio Simulation Using CrunchBase Data

How Machine Learning Is Changing Startup Predictions

How We Used Crunchbase Data to Predict Startup Success

Unicorns vs Failures: Constructing Comprehensive Datasets for Predictive Modeling

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps