Tracking China Vulnerability in Real Time Using Big Data: The CVSI Index

Big Data Empirics and Policy Analysis Conference Bank of England

Alvaro Ortiz., PhD* BBVA Research

*Casanova, C., La, X, Ortiz. A & Rodrigo, T (2017) “Tracking China Vulnerability in Real Time Using Big Data: The CVSI Index”. BBVA WP Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Summary

We have developed a China Vulnerability Sentiment Index using Big Data

The CVSI index allows us to track the 4 different vulnerability components: SOEs, Shadow Banking, Housing Bubble & FX speculative Robustness Check: “prior” inclusion of Sentiment Indicators is “Posterior” confirmed through Bayesian Model Averaging (BMA) No Systematic Bias between English & Chinese Sentiment in Local and foreign media but transitory deviations can affect market sentiment

Additional tools to track Risk in Real Time, with High Granularity and Geo- referenced Information. Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Index

01 Measuring Sentiment using GDELT

02 Estimation & Robustness Check

03 Results: The CSVI Index

04 Additional Risk Analysis Tools

Tracking Chinese Vulnerability in Real Time. Bank of England Conference

01 Measuring Sentiment Using GDELT Tracking Chinese Vulnerability in Real Time. Bank of England Conference

We introduce the Big Data (GDELT) analysis to track Different events, themes,

Tracking Chinese Vulnerability in Real Time. Bank of England Conference

We can extract more than 2300 emotions of more than 30000 topics in thousands of Newspapers of the world (Chinese & English) in real time

Economic Debt Tone

Housing Prices Tone

Economic Debt & Cosco Tone

Dic 6 Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Sentiment & Economics: References

Theoretical Literature • Pigou (1927): business cycle fluctuations are driven by expectations and entrepreneurs’ errors of optimism and pessimism are crucial determinants of these fluctuations • Keynes (1936) highlighted the importance of changes in expectations that are not necessarily driven by rational probabilistic calculations, but by “animal spirits” • Shiller (2017) shows “narratives” can explain aggregate fluctuations though epidemic models.

Empirical Literature • Angeletos, Collard and Dellas (2015) find that sentiment shocks account for around 1/2of GDP variance and 1/3 of the nominal interest rate variance at business-cycle frequencies. • Barsky and Sims (2012) found that this informational component forms the main link between sentiment and future activity in international business cycles. • Shapiro, Sudhoff, and Wilson (2017) show how the news sentiment measures outperform the University of Michigan confidence index Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Measuring Sentiment

Text Shallow Deep Sentiment Input Parsing Parsing Aggregation

푃표푠𝑖푡𝑖푣푒 푊 − 푁푒푔푎푡𝑖푣푒 푊 Sophisticated natural language Sentiment = 100 ∗ Print and web news media “Tokenization” or processing algorithms 푇표푡푎푙 푤표푟푑푠 in over 100 languages Sentences Positive W: This is the percentage of from across every country Assisted by nearly 40 all words in the article that were found Cleaning Texts “The”, “a” Dictionaries Including Harvard to have a positive emotional translated in real time to “:”, “.”… Urls.. IV, LM (2011) and Federal connotation. Ranges are normally from English and parsed Reserve Financial Stability -10 to +10. Roots Econom* verb* (2017)

Negative: This is the percentage of all … *Global Content Analysis words in the article that were found to Measures (GCAM) system have a positive emotional connotation. Loughran, T., McDonald, B., (2011). When is a liability not a liability? Textual analysis, Ranges from 0 to +100 dictionaries, and 10-Ks. Journal of Finance 66, 35-65 Correa,R Garud,K, Londono-Yarce,JM and Mislang, N. (2017) "Sentiment in central bank's financial stability reports“. Federal Reserve IFDP Tracking Chinese Vulnerability in Real Time. Bank of England Conference

02 Estimation and Robustness Check Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Tracking China Vulnerability in Real Time: Value Added from Big Data

Hard Data … provide accurate information Indicators but at lower frequencies and with delays… China Vulnerability Sentiment Market … Real Time but limited Information also Index Indicators influenced by global factors…

… complementing Hard-Soft-Markets Sentiment in Real Time “sentiment” on Special Indicators topics not quotes. Tracking Chinese Vulnerability in Real Time. Bank of England Conference

A Balanced set of Information in the Database: Hard Data, Markets and Sentiment

China Vulnerability Sentiment Index (CVSI)

SOE Vulnerability Housing Bubble Shadow banking FX Speculative Index Vulnerability Index Vulnerability Index Pressure Index (SOEI) (HBI) (SBI) (FXI) Principal Components Analysis on each component Tone Hard & Financial data

Total.profits (M) Mortages.loan (M) NPL.Ratio (M) Foreign.Reserves (D) Liabilties (M) GICS.Housing.Index (M) TSF.Aggregate.New Increase (M) CNY Exchange Rate (D) Housing.Price (M) Entrusted.Loans (M) CNH Exchange Rate (D) New.Construction (M) Wenzhou.Index (D) HICNHON.Index (D) 25% RealEst.Invest (M) 45% WMPs Acceptances (M) 35% 40% Real time sentiment indicators

State owned enterprises (D) Housing policy & institutions (D) Non bank financial institutions (D) Currency exchange rate (D) Resource misallocs &policy Housing markets (D) Asset management (D) Currency reserves (D) Failure (D) Housing prices (D) Bank capital adequacy (D) Capital account (D) Resource misallocs&SOEs (D) Housing construction (D) Financial sector instability (D) Macroprudential policy (D) Institutional reform & SOEs (D) Housing finance (D) Banking regulation (D) Exchange rate policy (D) Industry policy (D) Land reform (D) Infrastructure funds (D) Illicit financial flows (D) Industry laws and regulations (D) Financial vulnerability & risks (D) Local government and SOEs (D) Monetary & financial stability (D) Debt and SOEs (D) State financial institutions (D) 75% 55% 65% 60% Tracking Chinese Vulnerability in Real Time. Bank of England Conference

A two step procedure to extract common vulnerability factor from Hard data, Markets and News Sentiment

1st Step Estimation: Components 2nd Step Estimation: Index

1 SOEI = 훾1푥1+ 훾2푥2+ … + 훾10푥10 + 휖1

2 HBI = 훿1푦1+ 훿2푦2+ … + 훿11푦11 + 휖2 6 퐶푆푉퐼 = 휇1SOE + 휇2HB + 휇3SB + 휇4FX + 휀

3 S퐵퐼 = 훽1푧1+ 훽2푧2+ … +훽15푧15 + 휖3

4 퐹푋퐼 = 휌1푣1+ 휌2푣2+ … +휌10푣10 + 휖4

푤𝑖푡ℎ 휇 , 휇 , 휇 , 휇 푏푒𝑖푛푔 푡ℎ푒 푤푒𝑖푔ℎ푡 표푓 푒푣푒푟푦 푤𝑖푡ℎ 훾 , 훿 , 훽 , 휌 푏푒𝑖푛푔 푡ℎ푒 푤푒𝑖푔ℎ푡 표푓 푒푣푒푟푦 1 2 3 4 푖 푖 푖 푖 푐표푚푝표푛푒푛푡 𝑖푛 푡ℎ푒 푓𝑖푟푠푡 푝푟𝑖푛푐𝑖푝푎푙 푐표푚푝표푛푒푛푡 푣푎푟𝑖푎푏푙푒 𝑖푛 푡ℎ푒 푓𝑖푟푠푡 푝푟𝑖푛푐𝑖푝푎푙 푐표푚푝표푛푒푛푡 표푓 푡ℎ푒 푓표푢푟 components Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Results show the Importance of Sentiment

Chinese Vulnerability Sentiment Index (CVSI): Weights

SOE Vulnerability Housing Bubble Shadow Banking FX Speculative Pressure Variable (Type) Weight Variable (Type) Weight Variable (Type) Weight Variable (Type) Weight

Tota Profits (HD) 19.63 New Construction (HD) 16.37 Wenzhou Index (M) 16.58 Currency Exchange Rate (S) 19.94 Institutional Reform & SOEs (S) 12.37 Mortgages Loans (HD) 14.57 WMP Yields (M) 13.63 Exchange Rate Policy (S) 17.95 Debt & SOE (S) 11.92 Land Reform (S) 12.62 Infrastructure_funds (S) 10.92 Macroprudential_Policy (S) 15.33 Liabilities (HD) 10.62 Housing Price (HD) 11.6 NPL ratio (HD) 9.46 Hinchon Index (M) 13.84 Local Goverment & SOE (S) 9.75 Housing Construction (S) 10.59 State & Finantial Inst (S) 8.95 CNY Currency (M) 11.92 Industry Policy (S) 9.5 Housing_Prices (S) 10.05 Banking_Regulation (S) 7.28 Capital Account (S) 10.05 Resource Mis. & P. Failure (S) 8.18 Housing Policy & Institutions (S) 8.94 Financial Vulnerability (S) 6.82 CNH Currency (M) 8.73 SOE (S) 7.15 Housing Finance (S) 7.83 Asset_Management (S) 5.62 Illicit Financial Flows (S) 1.58 Industry Laws & Regulation (S) 5.28 Housing Markets (S) 6.71 Financial Sector Instability (S) 5.35 Foreign Reserves (S) 0.6 Resource Misaloc. & SOE (S) 5.61 GICS Housing Index (M) 0.36 Bank Capital Adequacy (S) 4.6 Currency Reserves (S) 0.06 Real State Investment (HD) 0.31 Non Bank Financial Inst (S) 4.35 Monetary & F.Stability (S) 3.54 Acceptances (HD) 2.22 TSF Aggregate New (HD) 0.57 Entrusted Loans (HD) 0.13

%of Sentiment in Component (S) 69.76 %of Sentiment in Component (S) 56.74 %of Sentiment in Component (S) 57.43 %of Sentiment in Component (S) 48.27

% of Variance by 1st PC 63.2 % of Variance by 1st PC 65.8 % of Variance by 1st PC 59.5 % of Variance by 1st PC 78.99 in the CSVI 29.18 Weight in the CSVI 26.05 Weight in the CSVI 23.12 Weight in the CSVI 21.64 Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Robustness Check: Co-movement (Hard-Market-Sentiment)

Chinese Vulnerability Sentiment Index Colour Map: Patterns and Comovements (Standard values. Light Blue values indicate a improvement of sentiment while dark blue stands for higher viulnerability sentiment) Source: own calculations 2015 2016 2017

MAR APR MAY JUN JUL AUG SEP OCT NOV DEC JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC JAN FEB MAR APR MAY JUN JUL AUG SEP Liabilties data Total profits data DEBT & STATE_OWNED_ENTERPRISES gdelt RESOURCE_MISALLOCATIONS_AND_POLICY_FAILUR & STATE_OWNED_ENTERPRISESgdelt INSTITUTIONAL_REFORMandWB_721_STATE_OWNED_ENTERPRISESgdelt STATE_OWNED_ENTERPRISES gdelt

INDUSTRY_POLICY gdelt SOE INDUSTRY_LAWS_AND_REGULATIONS gdelt INSTITUTIONAL_REFORMandWB_721_STATE_OWNED_ENTERPRISES.1gdelt RESOURCE_MISALLOCATIONS_AND_POLICY_FAILURE gdelt LOCAL_GOVERNMENTandWB_721_STATE_OWNED_ENTERPRISESgdelt LOCAL_GOVERNMENT gdelt Housing.Price data RealEst.Invest data mortages.loan data GICS.Housing.Index data New .Construction data HOUSING_POLICY_AND_INSTITUTIONS gdelt HOUSING_MARKETS gdelt ECON_HOUSING_PRICES gdelt WB_870_HOUSING_CONSTRUCTION gdelt Housing Bubble HOUSING_FINANCE gdelt LAND_REFORM gdelt Wenzhou.Index financial NPL.Ratio financial TSF.Aggregate.New Increased financial Entrusted.Loans financial WMPs financial Acceptances financial NON_BANK_FINANCIAL_INSTITUTIONS gdelt ASSET_MANAGEMENT gdelt BANK_CAPITAL_ADEQUACY gdelt FINANCIAL_SECTOR_INSTABILITY gdelt BANKING_REGULATION gdelt

Shadow Banking INFRASTRUCTURE_FUNDS gdelt FINANCIAL_VULNERABILITY_AND_RISKS gdelt MONETARY_AND_FINANCIAL_STABILITY gdelt STATE_FINANCIAL_INSTITUTIONS gdelt CNY.Curncy financial Foreign.Reserves financial HICNHON.Index financial CNH.Curncy financial ECON_CURRENCY_EXCHANGE_RATE gdelt

FX ECON_CURRENCY_RESERVES gdelt CAPITAL_ACCOUNT gdelt MACROPRUDENTIAL_POLICY gdelt EXCHANGE_RATE_POLICY gdelt ILLICIT_FINANCIAL_FLOWS gdelt Vulnerability Intensity: Low High Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Robustness Check: Do our selected variables account for “underlying” vulnerability

Posterior Inclusion Probability of a set of “X” candidates variables in explaining “Risk” (“Y”) ( Risk=y= proxied by Chinese CD Swap)

Zellner´s Uniform Prior (Non informative Prior, β=0)

Hyperparameter “g” shows certain is the researcher fo B to be zero Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Bayesian Model Averaging Robustness check confirms the relevance of Sentiment in explaining Market Risk proxies

Bayesian Model Averaging Results Bayesian Model Averaging Results: X with PIP>50% (PIP Inclusion after 1000 models) (PIP Inclusion after 1000 models) MODEL INCLUSION BASED ON THE BEST 1000 MODELS total.profits.yoy resource misallocations and policy failure&soe Dependent variable: CDS Spread Type of data Component PIP Posterior Mean Posterior standard deviation SD industry policy Total profits Hard Data SOE debt 1 1.000 -0.358 0.042 resource misallocations and policy failure 2 Institutional reform&SOE Sentiment SOE 1.000 -0.089 0.019 economic transparency Industry policy Sentiment SOE mortages.loan 3 1.000 -0.112 0.015 l&.sales 4 Economic transparency Sentiment Shadow Banking 1.000 -0.069 0.015 econ housing prices Hard Data price controls 5 mortages loan Housing bubble 1.000 1.014 0.105 entrusted.loans 6 housing finance Sentiment Housing bubble 1.000 0.086 0.016 acceptances Financial financial sector instability 7 NPL ratio Shadow Banking 1.000 -0.976 0.130 state financial institutions 8 Acceptances Financial Shadow Banking 1.000 -0.264 0.053 cny.curncy Financial hicnhon.index 9 CNY curncy FX 1.000 -0.811 0.086 foreign.reserves Econ currency reserves Sentiment FX cnh.curncy 10 1.000 0.129 0.020 exchange rate policy 11 Exchange rate policy Sentiment FX 1.000 -0.113 0.017 banking regulation Illicit financial flow s Sentiment FX infrastructure funds 12 1.000 0.063 0.015 institutional reform&soe 13 Industry law s and regulations Sentiment SOE 0.995 0.062 0.016 wmp.yields Financial state owned enterprises 14 Hicnhon index FX 0.994 0.080 0.022 govyield 15 State ow ned enterprises Sentiment SOE 0.953 -0.055 0.020 land reform Sentiment realest.invest 16 Econ housing prices Housing bubble 0.927 0.058 0.025 housing markets 17 Financial sector instability Sentiment Shadow Banking 0.908 0.089 0.038 housing finance liabilties.assets 18 Wenzhou index Financial Shadow Banking 0.860 0.071 0.040 capital account Asset managment Sentiment Shadow Banking econ currency reserves 19 0.817 0.042 0.025 local government 20 Banking regulation Sentiment Shadow Banking 0.791 0.032 0.020 bank capital adequacy Macroprudential policy Sentiment FX econ currency exchange rate 21 0.716 -0.030 0.023 new.construction 22 Housing policy and institutions Sentiment Housing bubble 0.706 0.030 0.023 asset management Hard Data illicit financial flows 23 New construction Housing bubble 0.697 0.045 0.035 financial vuln and risks 24 Entrusted loans Financial Shadow Banking 0.674 -0.072 0.058 gics.housing.index Hard Data local government&soe 25 Real Estate Investment Housing bubble 0.655 0.055 0.048 26 Non bank Financial institutions Sentiment Shadow Banking 0.655 -0.029 0.025 Tracking Chinese Vulnerability in Real Time. Bank of England Conference

03 Results: The CVSI index

Tracking Chinese Vulnerability in Real Time. Bank of England Conference

The index shows that Vulnerability sentiment has been improved since the authorities implemented some policies Chinese Vulnerability Sentiment Index (CVSI)

(Evolution of the “Tone” or “Sentiment”. Lower values indicate a deterioration of sentiment and higher vulnerability) (Lower Vulnerability)(Lower Improving Improving Sentiment 3

stock market crash, 2 Stock trade halted NPC Accepts Market RMB enters IMF's Lower Growth Crash SDR basket Target

1

0

(Higher Vulnerability) (Higher Worsening S&P’s Neutral Area +- 0.5 std Downgrade -1 Moody’s 3% Devaluation NPC meeting

Sentiment Downgrade -2 PMI falls "Black Monday" to 4Y lows

-3 High volatility and negative sentiment Low volatility and positive sentiment

18

Jul-15 Jul-16 Jul-17

Oct-16 Oct-17 Apr-15 Oct-15 Apr-16 Apr-17

Jun-15 Jan-16 Jun-16 Jan-17 Jun-17

Mar-15 Mar-16 Mar-17

Feb-17 Feb-16

Aug-15 Sep-15 Nov-15 Dec-15 Aug-16 Sep-16 Nov-16 Dec-16 Aug-17 Sep-17

May-15 May-16 May-17 Source: www.gdelt.org & Own Calculation s Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Some components have some an important response to policy changes (i.e Shadow Banking) CVSI: SOEs Component CVSI: Shadow Banking Component

(Evolution of the “Tone” or “Sentiment”.) (Evolution of the “Tone” or “Sentiment”.)

(Lower (Lower Vulnerability) Improving Improving Sentiment (Lower Vulnerability)(Lower 3.5 Improving Sentiment 3.5 NDRC and State Council promulgated the “Ten 2.5 rules” of SOE reform 2.5 Stock Market Crash 1.5 1.5

0.5 0.5

(Higher Vulnerability) (Higher Worsening (Higher Vulnerability) (Higher -0.5 Worsening -0.5 Stock Market Crash and RMB depreciation -1.5 Moody’s -1.5 Downgrade S&P

Sentiment Downgrade Sentiment -2.5 The start of Mixed -2.5 CBRC Guidance on SoE Mixed ownership ownership reform of Loan Beneficiaries Reforms Plan China Unicom rights Trandsfer

-3.5

-3.5

Jul-17 Jul-15 Jul-16

Jan-16 Jan-17

Mar-15 Mar-16 Mar-17

Sep-15 Nov-15 Sep-16 Nov-16 Sep-17

May-15 May-16 May-17

Jun-15 Jun-16 Jun-17

Mar-15 Mar-16 Mar-17

Dec-15 Dec-16

Sep-15 Sep-16 Sep-17 Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Other components present more random performance with some dependence of global affairs (External) CVSI: Real State Component CVSI: External

(Evolution of the “Tone” or “Sentiment”.) (Evolution of the “Tone” or “Sentiment”. (Lower (Lower Vulnerability)

Improving Improving Sentiment 3.5 (Lower Vulnerability)(Lower Improving Improving Sentiment 3.5

2.5 CFTS 2.5 Announcement

1.5 1.5 FED Confirms Exit path

0.5

0.5

(Higher Vulnerability) (Higher Worsening

(Higher Vulnerability) (Higher Worsening -0.5 -0.5

-1.5 -1.5 Sentiment

A series of tightening Sentiment measures were Large Chinese real FED Doubts -2.5 Sharp decline -2.5 FED announced the promulgated estate developers On Hawkish In Real State sold their land interest rate hike Stance DXY depreciated Investment sharply

-3.5 -3.5

Jul-16 Jul-15 Jul-17 Jul-15 Jul-17 Jul-16

Jan-16 Jan-17 Jan-16 Jan-17

Mar-15 Mar-16 Mar-17 Mar-15 Mar-16 Mar-17

Sep-15 Nov-15 Sep-16 Nov-16 Sep-17 Sep-15 Nov-15 Sep-16 Nov-16 Sep-17

May-15 May-16 May-17 May-15 May-16 May-17 Tracking Chinese Vulnerability in Real Time. Bank of England Conference

04 Additional Risk Analysis Tools Tracking Chinese Vulnerability in Real Time. Bank of England Conference

The CSVI is associated to other High Frequency Indicators as Growth and Market Risk

CVSI Index and Economic Activity (PMI) CVSI Index and Risk Premia (CDS) (index and net balance) (index and basis points Inverted)

2.5 53 2.5 50 2.0 60 2.0 53 1.5 1.5 70 52 1.0 1.0 80 0.5 52 0.5 90 0.0 51 0.0 100 -0.5 51 -0.5 110 -1.0 -1.0 120 50 -1.5 -1.5 130 -2.0 50 -2.0 140

-2.5 49 -2.5 150

2-jul-15 2-jul-16 2-jul-17

2-jul-16 2-jul-15 2-jul-17

2-sep-15 2-sep-16 2-sep-17

2-sep-15 2-sep-16 2-sep-17

2-nov-15 2-nov-16

2-ene-16 2-ene-17

2-nov-15 2-nov-16

2-ene-16 2-ene-17

2-mar-15 2-mar-16 2-mar-17

2-mar-15 2-mar-16 2-mar-17

2-may-15 2-may-16 2-may-17

2-may-17 2-may-15 2-may-16 Chinese Vulnerability Index (All Languages) Chinese Vulnerability Index (All Languages) China CDS (inverted) China PMI Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Chinese Vulnerability Sentiment Index: total news VS Chinese news Chinese Vulnerability Sentiment Index: total, Chinese and English (Evolution of the “Tone” of main followed themes about vulnerability in China in Madaring and Non –Translated- English )

3 No Systematic Bias in

2 English & Chinese

1 Language Media

0

-1 -2 Transitory divergences

-3 Can affect markets

Jul-15 Jul-16 Jul-17

Apr-17 Apr-15 Oct-15 Apr-16 Oct-16

Jun-15 Jan-16 Jun-16 Jan-17 Jun-17

Mar-15 Feb-16 Mar-16 Feb-17 Mar-17

Nov-15 Dec-15 Nov-16 Dec-16

Aug-15 Sep-16 Sep-15 Aug-16 Aug-17 Sep-17

May-15 May-16 May-17 Chinese Vulnerability Index (news in Chinese) Chinese Vulnerability Index (news in English) Tracking Chinese Vulnerability in Real Time. Bank of England Conference

It can be used to analyze vulnerability in a very granular way…

China SOE Sentiment Diffusion Map (sentiment on SOE) 2015 2016 2017

Soe Company MAR APR MAY JUN JUL AUG SEP OCT NOV DEC JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC JAN FEB MAR APR MAY JUN JUL AUG SEP China International Intellectech Dongfang Electric China Energy Conservation Environmental Protection Group China Aerospace Science China Coal Tech Harbin Electric China Datang China Guodian China Electronics Co Dongfeng Motor China Electronics Technology Group Corporation China Minmetal China Southern Pow er Grid China Telecom China National Travel Service Sinochem China National Chemical Engineering China United Netw ork China State Construction Engineering China Huaneng China Shipbuilding Industry Corp China Nuclear Energy Chalco Sinopec China Mobile China Shipbuilding Corp China National Aviation Holding China National Chemical Co China Communications Construction Sinosteel Corporation Shenhua Group China National Building Materials Group Ansteel Cofco China National Petroleum Corporation China National Salt Chinese State Grid Corporation China First Heavy Industries Cnooc China Nonferrous Metals China National Coal Group China Grain Reserves Tracking Chinese Vulnerability in Real Time. Bank of England Conference

Including Geo referenced risks

Geographical Analysis Housing Prices (sentiment on Housing Prices Tracking China Vulnerability in Real Time Using Big Data: The CVSI Index

Big Data Empirics and Policy Analysis Conference Bank of England

Alvaro Ortiz., PhD* BBVA Research

*Casanova, C., La, X, Ortiz. A & Rodrigo, T (2017) “Tracking China Vulnerability in Real Time Using Big Data: The CVSI Index”. BBVA WP